FieldRobin

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint=true and destructiveHint=false, so the description correctly avoids restating them. It adds useful behavioral context beyond the annotations by clarifying workspace scoping and the privacy boundary that private operational notes are not exposed. There is no contradiction with the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that front-loads the main action and resource, then adds one important qualifier. Every clause earns its place and there is no filler or duplication of schema details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool with no required parameters, no nested objects, and full schema coverage, the description covers purpose, scope, and privacy limitation. It does not describe output shape or pagination behavior, but annotations and schema provide enough context to select and invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so limit, query, and status are already fully documented with defaults, enum values, and descriptions. The description adds no parameter-level meaning, but the high schema coverage means the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb and resource — 'Lists complaint and recall risk records' — and scopes it to the authenticated workspace. It does not explicitly name or differentiate sibling tools, but the resource is specific enough to avoid obvious confusion with the broader search and report siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is for retrieving complaint and recall risk records for the current workspace. It does not provide explicit when-to-use versus when-not-to-use guidance or name alternatives such as routing-driving-risk, so usage context is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds the 'active' status filter and the 'one authorized customer' scoping constraint, which are useful, but it doesn't disclose pagination or error behavior. This is comparable to the get_calls calibration baseline.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that fronts the action and subject, with no redundant wording. Every part contributes meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a low-complexity read-only tool with good schema coverage, the description is mostly sufficient. However, the schema lists zero required parameters while the description implies customer_id is necessary for 'one authorized customer', leaving ambiguity about whether the tool can be called without it. The description doesn't resolve this.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with both limit and customer_id documented, so the baseline is 3. The description's phrase 'bounded status, source, urgency, and scheduling fields' could confuse agents by suggesting additional parameters that do not exist in the schema, rather than clarifying the two actual parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'Lists' with a clear resource ('service requests') and explicit scope: 'recent active' and 'one authorized customer'. This distinguishes it from siblings like get-service-request (single record) and search-service-requests (broader search).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for a single authorized customer's active requests, but it does not explicitly name alternatives or state when not to use this tool. There is no direct guidance on choosing this over search-service-requests or get-service-request.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the 'without posting or changing' phrasing mostly reinforces rather than extends them. The description adds the 'policy-aware' behavioral context, but it does not go into output format, authorization mechanics, or what happens if the review is not found. With annotations covering safety, this is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that front-loads the core action and then states the key constraint. Every part earns its place and there is no filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a simple two-parameter, read-only tool with full schema coverage and safety annotations, so the description is largely sufficient. The main gaps are that it does not describe the returned draft format or explicitly point to search-reviews as the source of review_id, but these are minor given the low complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both review_id and tone are already documented in the schema. The description adds little beyond tying the operation to 'one authorized review', so it does not need to compensate for missing schema detail. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Drafts'), a specific resource ('a policy-aware reply for one authorized review'), and explicitly clarifies the non-action ('without posting or changing the review'). This makes the tool clearly distinct from sibling preview and search tools by focusing on drafting a review reply.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear usage context: it is for drafting a reply to one authorized review, and it is not for posting or modifying the review. It does not explicitly name a sibling alternative or say 'use search-reviews to get review_id', but the boundary of when to use it is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With readOnlyHint and destructiveHint already true/false, the description adds useful behavioral context: results are authorization-scoped ('authorized') and field-bounded with addresses and notes explicitly excluded. This tells the agent what data it can expect without contradicting the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense sentence that front-loads the core behavior first and appends the key exclusions. There is no filler or repetition of the title/schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is adequate for a simple one-parameter read tool, but it leaves gaps: it does not enumerate which contact/lifecycle fields are returned, and the schema marks customer_id as not required, creating ambiguity about whether the tool can be called without an ID. With no output schema, those details matter.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% because the only parameter is already documented as the customer ID returned by search-customers. The tool description itself adds no further parameter semantics beyond the singular 'one customer' cardinality, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific operation (returns one customer) with a clear resource and a bounded field scope: 'bounded contact and lifecycle fields; addresses and notes are excluded.' This distinguishes it from sibling search/list tools and from other get-* resources.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The intended usage is only implied: a single customer lookup by ID, with the ID source given in the schema ('Customer ID returned by search-customers'). The description does not explicitly say when to prefer this over search-customers or other sibling tools, nor does it spell out exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The read-only annotations already establish safety, and the description adds meaningful behavioral detail: results are limited to authorized invoices and certain sensitive/display fields are intentionally absent. It does not describe error behavior or auth failure modes, but for a simple read-by-ID tool with safety annotations this is a small gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence earns its place: it names the action and resource, states the available fields, and lists exclusions. No filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter read tool with read-only annotations, the description gives enough shape of the response by listing the field groups and exclusions. There is no output schema, but the high-level return contract is clear; the main omission is explicit confirmation that invoice_id is required.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single parameter is fully documented by the schema ('Invoice ID returned by search-invoices'), so the description adds no extra parameter-level meaning. With 100% schema coverage, the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ('Returns one authorized invoice') and then narrows the contract by naming the included field groups and the excluded ones. This makes it easy to distinguish from siblings like search-invoices (list vs. one) and preview-invoice (bounded vs. excluded fields).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use or when-not-to-use guidance, and no sibling is named as the alternative for excluded fields such as payment links or addresses. The usage context is only implied by 'one authorized invoice' and by the schema note that invoice_id comes from search-invoices, which is adequate but leaves routing decisions to the agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish read-only and non-destructive behavior, so the description adds meaningful context beyond them: the result is 'authoritative,' limited to one invoice, and deliberately omits sensitive data like payment links and provider identifiers. This gives an agent useful privacy and access-control expectations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one tightly worded sentence that front-loads the core behavior and then adds the key privacy constraint. Every clause carries meaning, with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple single-parameter read-only tool, the description plus schema provides enough to call it correctly. The main gap is that no output schema exists and the possible payment-state values are not enumerated, but the core purpose and parameter source are clear.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, and invoice_id is clearly described as the ID returned by search-invoices. The tool description itself adds no additional parameter-level meaning, so the baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Returns the authoritative payment state for one authorized invoice.' It also distinguishes itself from sibling tools like get-invoice and preview-invoice by explicitly noting it does not expose payment links or provider identifiers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given for when to use this tool versus alternatives such as get-invoice or preview-invoice. The schema's note that invoice_id comes from search-invoices hints at provenance, but the description itself does not establish selection criteria or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark the tool as readOnly and non-destructive. The description adds value by specifying the field scope (bounded and excluded) and the 'authorized' aspect, which informs the agent about response limitations. There is no contradiction with the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that front-loads the action and resource, then efficiently communicates the field boundaries. Every word earns its place without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Without an output schema, the description conveys the essential response scope: it returns a single job with certain field groups and excludes others. This is adequate for a simple one-parameter tool, though it could be more explicit about the exact fields included. Overall, it is substantially complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema fully covers the single parameter (job_id) with a descriptive note about its source. The tool description does not add any parameter-specific information beyond what the schema provides, so with 100% schema coverage the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Returns one authorized job') and the resource ('job'), and specifies the scope of returned fields ('bounded customer, schedule, status, and technician fields') plus exclusions ('service addresses, notes, and amounts'). This differentiates it from sibling tools that return other entities or multiple jobs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for retrieving a single job by ID, as it says 'Returns one job'. However, it does not explicitly mention when to use this tool instead of alternatives like search-jobs or jobs-today, nor does it state exclusion conditions. The schema description does provide the origin of the job_id, but that is outside the tool description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish readOnlyHint=true and destructiveHint=false, lowering the burden. The description adds useful behavioral context by stating the result is limited to authorized leads and explicitly excluding notes, budget, and internal summaries—information an agent would not get from annotations alone.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, well-structured sentence that front-loads the action and resource, then efficiently communicates field scope and exclusions. Every clause adds value and there is no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only, single-parameter lookup, the description covers included and excluded fields reasonably well. The main gap is that lead_id is not marked as required in the schema, and the description does not explicitly state that it must be supplied, though it is clearly the only parameter.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the lead_id parameter is already well described as 'Lead ID returned by search-leads.' The tool description adds no additional parameter-level meaning, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Returns') and resource ('one authorized lead'), and clarifies the scope by naming included field categories and explicit exclusions. This makes it clearly distinct from search-leads and the other get-* siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The singular 'one authorized lead' implies this is a detail lookup rather than a search, and the lead_id comes from search-leads. However, the description does not explicitly state when to use this tool over search-leads or other get-* tools, nor does it provide any when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds one useful interpretive caveat about Google listing status versus Business Profile connection, but it does not disclose error behavior, output details, or other edge cases. This is acceptable for a simple getter but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with no wasted words. The core behavior is front-loaded, and the second sentence is a meaningful clarification rather than filler or restatement of the title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a low-complexity, one-parameter, read-only getter, the description is mostly complete: it names the returned resource and the distinctive status field, while the schema supplies the parameter. The lack of an output schema is mitigated by the summary of what is returned, though a bit more usage direction would round it out.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage and already documents location_id as a 'Location ID'. The description adds no extra meaning about the parameter's format, constraints, or behavior beyond that. With full schema coverage, the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Returns'), the resource ('one location'), and the key data returned ('public Google listing status'). The caveat about confirmed places not being Google Business Profile connections adds semantic precision. However, it does not explicitly name sibling tools like search-locations, so differentiation is implicit rather than explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'Returns one location' implies this is the single-record lookup counterpart to search-locations, but no explicit when-to-use guidance is given. There are no named alternatives or exclusions, so an agent must infer usage from the description and sibling names.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish read-only and non-destructive behavior. The description adds meaningful output-contract transparency by stating the estimate is authorized, singular, field-bounded, and that addresses, notes, and terms are excluded. This goes beyond the annotations by telling the agent what it will and will not receive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single tightly written sentence with zero filler. It front-loads the core action and resource, then appends the exclusions in the same clause. The title 'Get Quote Tool' is not needlessly repeated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple single-ID retrieval with read-only annotations, the description covers selection criteria, how to obtain the ID, and the output field scope and exclusions. Minor ambiguity remains around the meaning of 'authorized' and the schema does not mark quote_id as required, but these gaps are small relative to the overall clarity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single parameter quote_id is fully described in the schema as 'Estimate ID returned by search-quotes,' so schema coverage is 100% and the description need not add much. The description adds no extra parameter semantics beyond the schema, but the schema already carries the meaning. The missing required declaration is a schema issue, not a description gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Returns one authorized estimate' and enumerates the exact field categories included and excluded. The singular 'one' and the estimate scope clearly distinguish it from plural search tools like search-quotes and from preview-quote, preview-invoice, and get-invoice.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied: the tool returns a single authorized estimate and explicitly excludes addresses, notes, and terms, signaling when not to use it. The parameter description also tells the agent to obtain quote_id from search-quotes. However, the description never names an alternative tool for previewing quotes or retrieving the excluded fields, so the guidance is not fully explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint=true and destructiveHint=false. The description adds genuinely useful behavioral information beyond that: the returned data is 'verified' and the tool intentionally omits referral tokens and bearer-like links. This security-relevant detail is not available from annotations or the schema alone.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single well-formed sentence with no filler. The primary purpose is front-loaded, and the security caveat is placed naturally at the end where it adds value without obscuring the main action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with two optional parameters, the description is adequate for selecting and invoking it. However, there is no output schema, and the description only vaguely says 'totals and conversion activity' without detailing the expected metrics or response shape, leaving some ambiguity about what exactly will be returned.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the schema clearly defines 'days' as a lookback window and 'campaign_id' as the ID returned by search-referral-campaigns. The description itself adds no parameter-specific semantics, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the action and resource: it 'shows verified referral campaign totals and conversion activity.' It also adds a meaningful differentiator by stating that referral tokens or bearer-like links are not returned, which helps distinguish it from campaign preview/search siblings. It stops short of naming the sibling it complements, so it is not a perfect 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied by the security-focused caveat: this tool is appropriate when the agent needs totals/conversion activity without exposing tokens or bearer-like links. However, the description never explicitly says when to use this over preview-referral-campaign or search-referral-campaigns, so the guidance remains implicit rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, covering safety. The description adds value by disclosing that the tool returns only bounded status, source, urgency, and scheduling fields, and explicitly excludes descriptions, addresses, contact channels, metadata, files, and outreach controls. This behavioral detail about field filtering goes beyond what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that front-loads the action and resource, then elaborates on the field restrictions. Every part of the sentence adds value; there is no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is adequate for a simple get tool with one parameter. It explains what the tool returns (field categories) and what it excludes. However, it does not list the exact fields within the categories ('status, source, urgency, scheduling fields'), which might leave an agent uncertain about the precise output. Given the lack of an output schema, this is a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single parameter's description in the schema already explains its meaning and origin ('Service-request ID returned by search-service-requests'). The tool description adds no additional semantic information about the parameter, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (returns), the resource (one authorized service-request inbox record), and the scope (bounded status, source, urgency, scheduling fields). It also explicitly lists what is NOT exposed, which distinguishes this from search-service-requests and other get-* tools. The specificity of the field restrictions makes the purpose unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool versus alternatives. It implies a workflow through the parameter description ('Service-request ID returned by search-service-requests'), but the description itself lacks guidance on selecting this over search-service-requests or other sibling tools. No exclusions or conditions are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds the qualifier 'limited' and clarifies the workspace must be authenticated, which is useful context. However, it largely mirrors the existing readOnlyHint annotation and does not disclose additional behavioral details such as the specific data included or any access constraints beyond authentication.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, tight sentence with no filler. The key information—return type, scope, and safety—is front-loaded and every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter, read-only tool, the description is largely sufficient: the agent knows what action to take and that the result is a safe, limited summary. Since there is no output schema, a slightly more detailed description of what the summary contains would improve completeness, but it is not essential for invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the description has no parameter semantics to explain. The baseline for zero-parameter tools is 4, and the description appropriately focuses on the return value rather than nonexistent inputs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Returns') and resource ('summary of the authenticated FieldRobin workspace'), making the tool's purpose immediately identifiable. It distinguishes itself from sibling tools by addressing the workspace as a whole rather than individual records, though the exact contents of the summary are left unspecified.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied: the tool should be used when a workspace summary is needed. However, there is no explicit guidance on when to prefer it over alternatives or any exclusion criteria, though no sibling tool appears to offer the same scope.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, covering the safety profile. The description adds that jobs are 'authorized' and that fields are 'bounded', but does not disclose return format, pagination behavior, or empty-result behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence with no filler. It front-loads the main action and scope, and every qualifier ('authorized', 'business day', 'bounded') earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with four optional parameters, full schema coverage, and safety annotations, the description adequately conveys scope and output field categories. A fully enumerated return schema would be nice, but nothing essential for invoking the tool correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so all four parameters, including defaults and constraints, are already fully documented. The description adds only the general 'bounded fields' concept and no per-parameter meaning, matching the baseline for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Lists' and the resource 'jobs', with a specific scope: 'scheduled for a business day' and 'bounded...fields'. It distinguishes the tool from broader siblings like search-jobs and get-job by implying a narrow, date-scoped view, though it does not name an alternative.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this is the tool for a quick day-scoped jobs lookup, but it gives no explicit when-to-use guidance or exclusions. It does not mention when to prefer search-jobs or get-job instead.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this as read-only and non-destructive. The description adds meaningful behavioral context by stating the photos are 'authorized private' and that the URLs are 'protected,' signaling access-control requirements and that the URLs are not general public links. This goes beyond the annotation metadata without contradicting it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single well-constructed sentence that front-loads the core action and scope ('Lists authorized private photos attached to one job') before listing the returned fields. Every word contributes meaning, with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter read-only listing tool with no output schema, the description is complete enough: it states the scope, the kinds of data returned, and the protected nature of the URLs. No missing information is needed for an agent to select and invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The only parameter, job_id, already has a complete schema description ('Job ID returned by search-jobs'), so schema coverage is 100%. The description adds little parameter-level detail beyond reinforcing the 'one job' scope, which is appropriate at the baseline for fully documented parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'Lists' and names the resource: 'authorized private photos attached to one job.' It further enumerates the kinds of data returned (protected download URLs, filenames, captions, media types), making the tool's purpose unambiguous and distinct from broader job or search tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'attached to one job' provides clear context for when to use this tool: when the agent needs the photos belonging to a specific job. It does not explicitly name alternative tools or state exclusions, but no sibling tool appears to offer this same photo-listing capability, so the guidance is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description doesn't need to restate safety. It adds useful behavioral context by disclosing the bounded nature of the result and explicitly stating what is not exposed (amounts, item pricing, private notes). This goes beyond the structured annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single well-structured sentence with no filler or repetition. It leads with the verb and resource, then scope, then exclusions. Every clause contributes meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with two optional parameters and no output schema, the description covers the essential data categories and privacy boundaries. It is slightly short of complete because it does not describe the response shape or how the optional technician_id affects the returned data, but these are minor gaps given the schema coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the input schema already documents both limit and technician_id. The description adds little parameter-specific meaning beyond implying a bounded result set; it does not introduce format details or relationships between the parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Reads') and names the exact resources: bounded parts stock, technician exposure, and transaction metadata. It also scopes the operation to the authenticated workspace and contrasts it with what it does not expose, which helps distinguish it from sibling tools like search-inventory.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no explicit guidance about when to choose this tool over alternatives, and it does not mention any sibling tool or exclusion condition. Usage is only vaguely implied by the word 'Reads'; there is no contextual direction such as 'use this for bounded operational data, search-inventory for full inventory details.'

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate this is read-only and non-destructive. The description adds meaningful context by promising not to expose coaching notes or private contact fields, which is a useful privacy behavior beyond the annotation. 'Bounded' also hints at limited scope, though the exact bound is not detailed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence that front-loads the action and resource, then adds the key privacy qualifier. There is no filler, repetition, or extraneous detail; each part earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a low-complexity read tool with zero required parameters and a fully covered schema, the description covers the essential scope and privacy boundary. It could be slightly richer by clarifying what 'coaching signals' includes, but nothing critical is missing for an agent to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both `limit` and `technician_id` are already documented in the input schema. The description does not need to add parameter-level detail, and it does not meaningfully go beyond the schema. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb ('Reads') and names a concrete resource: bounded technician performance and coaching signals for the authenticated workspace. It also differentiates itself by stating what it excludes (coaching notes, private contact fields), making its scope clear relative to sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is appropriate when an agent needs technician performance or coaching signals within the authenticated workspace. However, it does not explicitly say when to prefer this over a sibling tool or when not to use it, leaving some inference to the agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this by stating the tool does not change, dismiss, or execute items. It adds the contextual detail that results are scoped to the authenticated business and are persisted attention items, but it does not reveal other behavioral traits such as pagination behavior or authorization requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no filler. It front-loads the core action and resource, then adds a useful non-mutation qualifier. Every phrase contributes to the agent's understanding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only list tool with no required parameters, no output schema, and fully documented input fields, the description is largely adequate. The main gap is not explaining how this tool relates to pipeline-recommendations or when a search/preview sibling would be more appropriate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the input schema fully documents all five optional parameters. The description adds no parameter-specific meaning beyond the schema, which aligns with the baseline of 3 where the schema carries the burden.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb ('Lists'), a clear resource ('persisted pipeline attention items'), and explicitly communicates a non-mutating scope ('without changing, dismissing, or executing them'). It is clear and specific, though it does not explicitly differentiate itself from sibling tools like pipeline-recommendations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to use this tool versus alternatives such as pipeline-recommendations or the many preview/search siblings. There is no stated condition, exclusion, or alternative tool reference, so an agent must infer usage purely from the name and description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, lowering the bar. The description adds meaningful context: the recommendations are 'persisted,' scoped to the authenticated business, and no side-effectful operations are performed. This goes beyond the bare annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence that conveys scope, target, and non-behaviors without any fluff. Every word contributes to the agent's understanding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only listing tool with fully documented optional parameters and safety annotations, the description is nearly complete. It could be slightly stronger by naming a sibling for mutation flows or describing the result shape, but no output schema makes that less critical.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All five parameters are fully documented in the schema with descriptions and defaults, so the description does not need to repeat them. The description itself says nothing about parameters, which is acceptable because the schema carries the full semantic weight.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Lists'), a specific resource ('persisted pipeline recommendations'), and a clear scope ('for the authenticated business'). It also explicitly differentiates the tool from any mutation-oriented pipeline tool by listing what it does not do.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly communicates that this is for read-only listing and explicitly excludes generating, editing, approving, rejecting, or executing recommendations. It does not name a specific alternative tool, but the context makes when-to-use reasonably clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and destructiveHint, so the description adds value by explicitly stating 'without sending or changing records' and by noting that suppression and policy skips are included. This expands on the annotation profile without contradicting it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence contains the core action, the target resource, what is included, and the non-mutating guarantee. There is no redundant or filler wording.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple two-parameter schema, full schema coverage, and read-only annotations, the description is sufficient for an agent to understand the tool's main constraints. It does not detail the output shape, but no output schema exists and the core behavior is well covered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with both limit and campaign_id fully described in the input schema. The description adds context about the audience being 'approved' and 'one,' but does not meaningfully expand parameter semantics beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific action ('Previews') and resource ('one approved broadcast audience'), and clarifies scope with 'suppression and policy skips.' It also distinguishes itself from the sibling preview tools by specifying broadcast campaign rather than reactivation or referral campaigns.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The intended use is implied: inspect a single approved broadcast audience before any send. However, it does not explicitly name alternatives or state when not to use this tool, leaving the agent to infer the right context from sibling tool names.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and destructiveHint, but the description adds specific behavioral traits: 'deterministic' and a detailed list of omitted actions (save, charge, send, create). This goes beyond the annotations by specifying exactly what side effects are avoided, which is valuable context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence that front-loads the primary action and then lists exclusions concisely. Every word contributes, with no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 7 parameters and no output schema, the description fails to indicate what the preview contains (e.g., totals, tax breakdown) or how the inputs affect the result. The minimal text does not give an agent enough to predict the outcome or construct valid input, making it incomplete for a tool of this complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 29%, and the description provides zero insight into parameters like items, tax_mode, coupon_code, or tax_rate_id. It does not compensate for the low schema coverage, leaving agents without meaning for most fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the specific verb 'Calculates' and resource 'invoice preview', and explicitly lists what it does not do (saving, charging, sending, creating). This differentiates it from other preview tools and establishes its role as a pure computation tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when a non-persistent invoice preview is needed, but it does not mention alternatives (e.g., preview-quote) or provide explicit when-to-use/when-not-to-use guidance. It excludes side effects but does not compare with sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds behavioral details beyond the annotations by stating it is deterministic and does not save, send, or create. This aligns with the readOnlyHint and destructiveHint=false annotations. However, it does not disclose potential error conditions or failure modes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that front-loads the primary action. It avoids unnecessary detail and is well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description lacks information about the output format or what the preview contains (e.g., breakdown, totals). It also does not explain edge cases like empty items or invalid coupon codes. Given the complexity of the input schema, this leaves gaps in understanding the tool's full behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 29%, and the description does not explain the meaning or expected values of most parameters. It only mentions 'items' and 'customer_id' in the schema, but the description text itself does not elaborate on parameter usage, leaving ambiguity for parameters like tax_mode, coupon_code, and discounts.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: it calculates a deterministic estimate preview. It explicitly specifies what it does not do (saving, sending, creating), distinguishing it from other preview tools. The verb 'calculates' and resource 'estimate preview' are specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for previewing without committing, but it does not explicitly state when to use this tool versus alternatives such as preview-invoice or preview-broadcast-campaign. There is no explicit guidance on when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds the concrete guarantee 'without sending or changing records' and notes the 'authorized' single-campaign scope, which is useful but does not add return format or pagination behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that front-loads the action and resource, then adds a meaningful safety qualifier. There is no filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only two-parameter preview tool, the description combined with schema and annotations is nearly complete. The only notable gap is the absence of what the preview return value looks like, but no output schema is declared and the meaning is largely inferable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters are already documented well: limit has min/max/default, and campaign_id notes it comes from search-reactivation-campaigns. The description's phrase 'one authorized reactivation campaign' reaffirms campaign_id but does not add substantive meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Previews') and a specific resource ('dormant customers eligible for one authorized reactivation campaign'). It also explicitly distinguishes itself from sending or changing records, which differentiates it from campaign-sending siblings and other preview tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool: to safely see which dormant customers are eligible for one reactivation campaign. However, it does not explicitly state when not to use it, nor does it point to search-reactivation-campaigns as the way to obtain campaign_id beyond what the schema already says.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful context ('without sending or changing records,' 'eligible completed jobs'), but it does not disclose additional behavioral details such as auth requirements, rate limits, or pagination behavior. There is no contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, compact sentence communicates the tool's purpose, scope, and side-effect-free nature. It is front-loaded with the action and includes no filler or redundant restatement of the title/name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter, read-only preview tool with full schema coverage, the description is largely sufficient. The only minor gap is that there is no output schema and the description does not explicitly state what fields or format the preview returns, but 'previews eligible completed jobs' gives a reasonable indication.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters are already documented: campaign_id is tied to search-referral-campaigns and limit has a clear description and bounds. The main description adds little beyond the schema, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Previews'), a specific resource ('eligible completed jobs'), and a clear scope ('for one authorized referral campaign'). It also adds the crucial qualifier 'without sending or changing records,' which distinguishes it from campaign execution tools and from sibling preview tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description makes the usage context clear: it is a read-only preview of eligible jobs for a referral campaign, meant to inspect before sending. It does not explicitly name alternatives or give when-not-to-use conditions, but the combination of 'previews' and 'without sending or changing records' gives an agent clear context for safe selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish read-only and non-destructive behavior, and the description reinforces this with 'without sending anything.' It further discloses that the tool evaluates eligibility and reports skip reasons, adding meaningful behavioral context beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence of about 15 words that front-loads the verb and scope, then adds the critical no-side-effect guarantee. There is no filler or redundant restatement.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter read-only preview tool, the description covers purpose, side-effect profile, and the nature of the output. The lack of an output schema is partially offset by mentioning eligibility and skip reasons, though behavior when job_ids is omitted is left unclear.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the parameter meanings are already fully documented. The description adds a 'completed jobs' qualifier relevant to job_ids but does not elaborate on channel semantics, so it neither meaningfully enhances nor conflicts with the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb, 'Previews,' and identifies both the resource ('completed jobs for review requests') and a distinctive output ('eligibility and skip reasons'). It clearly differentiates this from sending or drafting tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'without sending anything' establishes clear context for a dry-run/preview use case, and 'explicit completed jobs' tells the agent which inputs are relevant. It does not name an alternative tool for actually sending, so exclusion guidance is only implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint and destructiveHint annotations already signal a safe read-only operation, and the description reinforces this with 'without saving or publishing it.' It adds useful context about the validation purpose, though it does not specify what a successful or failed validation outcome looks like.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence with no filler. The central action ('validates social post copy'), the qualifier ('for an authorized source review'), and the safety boundary ('without saving or publishing it') are all front-loaded and necessary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a non-destructive validation tool with fully documented optional parameters, the description is largely sufficient. The main gap is that there is no output schema and the description does not clarify what 'validates' returns (e.g., error list, success flag), though the intent is reasonably inferable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all three parameters adequately. The description adds no additional parameter-level detail, which is acceptable given the high coverage; the baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('validates') with a clear resource ('social post copy') and explicitly states the key boundary: 'without saving or publishing it.' This differentiates it from sibling preview tools and draft mutation tools like draft-review-reply.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly conveys this is for safe validation of social draft content rather than committing it. It does not, however, explicitly name alternative tools like search-social-drafts or preview-broadcast-campaign or state when those should be preferred.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only and non-destructive. The description adds clarity by explicitly stating that mutation access is not exposed and location writes remain on the in-product assistant, which reinforces the read-only behavior and provides extra context beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, consisting of two sentences. It front-loads the main purpose and then lists exclusions, making it well-structured and easy to parse without unnecessary verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only reporting tool with no output schema, the description is complete: it states what the tool does, what it does not expose, and clarifies the scope of read-only operations. Nothing essential is missing for an agent to decide whether to call it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema fully covers the only parameter 'period' with an enum and clear description. The tool description adds no additional semantic information about the parameter, so a baseline score of 3 is appropriate given high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: comparing revenue, activation, retention, and review-request outcomes by physical location. This is a specific verb and resource, and the exclusions (customer names, invoice rows, mutation access) help distinguish it from sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool (for location-based comparison) but does not explicitly state when to choose it over alternatives. It mentions exclusions that hint at non-applicable scenarios, but lacks direct contrast with sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark this as read-only and non-destructive. The description adds valuable behavioral context beyond that: it specifies the data source ('all paid, non-sample invoices'), the aggregation ('aggregate customer totals'), and the output shape ('without invoice rows'). This goes beyond the annotations without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no fluff. The primary action and scope are front-loaded, and the additional details (invoice filtering, output format) are concise and relevant. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description partially explains the return: 'returns aggregate customer totals without invoice rows'. This gives a high-level understanding, though it omits specifics like ordering or exact fields in each result. For a simple read-only report with well-documented parameters, this is sufficient but not exhaustive, so a 4 is warranted.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema covers 100% of parameters with meaningful descriptions (period, from, to, limit). The tool description does not add any extra context about parameters, but since the schema is comprehensive, the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('ranks'), a specific resource ('named customers'), and the basis ('paid invoice revenue'), along with the workspace scope and the filtering of sample invoices. It clearly distinguishes this report tool from any general search or other report sibling by its singular focus on customer revenue ranking.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when this tool is useful (when you need a customer revenue ranking), but it does not explicitly mention alternatives or when not to use it. There are sibling report tools like reports-by-location and reports-overview, but no cross-referencing; the implied usage is still apparent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description transparently states the tool is read-only and does not expose sensitive data or mutation capabilities. It also notes it operates for the authenticated workspace. However, it does not describe the response format or any potential side effects, which, given the annotations already indicate read-only, adds value but is not fully comprehensive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that includes essential information about the tool's purpose and limitations. There is no unnecessary verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the tool's core functionality, exclusions, and workspace context. The parameter is well-documented. It does not specify the exact output structure, but for an aggregate report, the provided detail is sufficient. Minor missing info about return format is acceptable given no output schema exists.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The only parameter 'period' is clearly defined in the schema with a description, enum values, and a default. The tool description adds 'bounded trend metrics' for extra context. The parameter semantics are fully covered and well-explained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool reads aggregate performance metrics for revenue, receivables, jobs, leads, and estimates. It explicitly lists what it does not expose (customer names, addresses, invoice rows) and that it does not allow mutations, which helps distinguish from sibling tools that might handle detailed or sensitive data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool over alternatives. It implies it is for aggregate overviews, but lacks direct comparisons or conditions. There is no mention of 'use this when' or 'instead of' specific sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context: it reads a local business day route, focuses on high driving-risk stops, and deliberately omits addresses and private route notes. This goes beyond the annotations by explaining the privacy-preserving behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, well-structured sentence that front-loads the core action ('Reads a local business day route and high driving-risk stops') and adds the privacy qualifier without waste. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only tool with no output schema and full parameter documentation, the description covers the essential context: what is read, the scope (authenticated workspace), and what is intentionally excluded. It could mention pagination or the meaning of 'high driving-risk stops' in more detail, but the annotations and schema cover the rest.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all three parameters (date, limit, technician_id). The description does not add parameter-specific details beyond what the schema provides, but it does clarify the overall output scope (route and high-risk stops), which indirectly helps interpret the parameters. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool reads a local business day route and high driving-risk stops, and explicitly notes it does not expose addresses or private route notes. This distinguishes it from sibling tools like complaint-recall-risk or customer-service-requests, which focus on different risk/request domains.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this is for retrieving route and driving-risk data for the authenticated workspace, and the privacy note ('without exposing addresses or private route notes') gives context on what it is safe to use for. It does not explicitly name alternative tools or state when not to use it, but the sibling list and the specific scope make the usage context reasonably clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and destructiveHint, so the safety profile is covered. The description adds useful behavioral context beyond annotations by introducing 'verified busy jobs' and 'open planning windows,' and it reinforces that no scheduling or job mutation occurs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The entire description is one compact sentence that front-loads the core purpose and behavior. There is no filler or redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only calculation tool with no output schema, the description states the outputs at a high level (verified busy jobs and open planning windows) and includes the local-business-day context. The main gap is that it doesn't describe the exact response representation, but the tool is still adequately scoped for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All six parameters are fully described in the schema with defaults, ranges, and formats. The description adds no additional parameter-level meaning, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Calculates') and names a clear resource ('verified busy jobs and open planning windows') for a defined scope ('a local business day'). It also explicitly states what the tool does not do ('without scheduling or changing a job'), which helps distinguish it from write-oriented tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear usage context: use this tool when you need to compute availability and busy periods for a business day. It stops short of naming sibling alternatives or explicit when-not-to-use conditions, so it doesn't reach a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish this is read-only and non-destructive, so the description only needs to add behavioral context. It adds the 'authorized' scoping and the search dimensions, but does not clarify how results are bounded or whether the 'bounded delivery fields' correspond to visible schema properties.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One compact sentence front-loads the verb and resource and then lists the distinguishing filters. There is no filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only search with three optional, fully documented parameters, the description is mostly complete. The only gap is the ambiguous 'bounded delivery fields' phrase and the absence of any return-format note, but the lack of an output schema is mitigated by the obvious list-of-campaigns result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already documents all three parameters with 100% coverage, so the baseline is 3. The description restates name/channel search, which is in the query parameter description, and introduces the vague 'bounded delivery fields' without mapping it to a schema field, adding little beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear action ('Searches') on a specific resource ('authorized broadcast campaigns') and names the filter dimensions (name, status, message channel, and delivery bounds), which separates it from sibling search/preview tools for other campaign types. The resource label 'broadcast campaigns' is enough to avoid confusion with search-reactivation-campaigns or preview-broadcast-campaign.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the resource and action: use it when you need to find broadcast campaigns. However, there is no explicit guidance about when to prefer this over related siblings such as preview-broadcast-campaign or when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true and destructiveHint=false, so the tool is known to be safe. The description adds beyond these by stating it does not expose addresses, notes, or other private fields—an explicit behavioral trait about data filtering. This is valuable context not available in the annotations and is consistent with them. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence. It front-loads the primary action and scope, then appends a useful qualifier about privacy. Every word earns its place; there is no filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only search tool with two optional parameters and no output schema, the description is nearly complete. It communicates the search target and the privacy filter, which is sufficient for an agent to call it correctly. A minor omission is the lack of explicit mention that it returns a list of matches, but that is implicit for a search tool and covered by the absence of an output schema (no expectation of a single object). Overall, adequate without being exhaustive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already describes both parameters with full coverage (100%): 'limit' as max customers and 'query' as search terms. The description does not add parameter-level meaning beyond what the schema provides, so a baseline score of 3 is appropriate. No extra clarification is needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('searches') and resource ('customers'), and clarifies scope ('authenticated workspace customers'). It also distinguishes itself by noting it does not expose private fields, which helps separate it from other search tools like search-leads or search-invoices. Clear, specific, and differentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage: it is a search operation for customers, with the added qualifier that it avoids private fields, which informs selection when sensitive data should be omitted. However, it does not explicitly mention alternatives (e.g., get-customer for detailed info) or when not to use it. This is a minor gap but the context is clear enough for an agent to route appropriately.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark this as read-only and non-destructive, and the description adds useful behavioral context: workspace scoping and a data-exposure guarantee that cost/margin fields are not returned. It does not describe pagination or sort order, but that is not critical for this simple search tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded sentence that moves from verb and object to constraints and data restrictions. Every clause earns its place with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only search tool with four optional, fully documented parameters, the description covers purpose, scope, and an important output restriction. There is no output schema, but the explicit exclusion of cost/margin fields gives agents a meaningful picture of what results include and omit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% parameter description coverage, so the description does not need to repeat parameter detail. It aligns with the active and low_stock parameters but adds no semantics beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb and resource ('Searches active inventory'), adds a distinct use case ('identify low-stock items'), and signals a data-boundary behavior ('without exposing internal cost or margin fields'). This is enough to separate it from sibling search tools even without naming an alternative.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear context: use this for active inventory in the authenticated workspace, and specifically for low-stock identification. It does not name alternatives or explicit when-not conditions, but the scope is sufficiently clear among the sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish that the tool is read-only and non-destructive; the description adds that it only sees authorized invoices and that payment links and addresses are excluded. However, it also claims bounding by due-date and total fields that are not backed by the schema, and with no output schema it leaves the result shape unspecified.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence with the action and scope in the first clause, followed by the key exclusion. No filler or repetition of schema details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 6-parameter read-only search with no output schema, the description gives the search surface and exclusions but omits result format and any pointer to a sibling (e.g., get-invoice) for full invoice details. The phantom due-date/total references also leave an incomplete and slightly inaccurate picture.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline applies; each parameter already has its own description in the schema. The tool description adds only a high-level grouping of customer, job, status, and payment fields, and introduces due-date/total terminology that does not map to any actual parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific operation ('Searches') and resource ('invoices'), and clarifies that it covers authorized invoices with an enumerated set of search fields. It does not explicitly distinguish itself from siblings like get-invoice or preview-invoice, and it references due-date and total fields that are absent from the input schema, which slightly blurs the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given about when to use this tool instead of alternatives such as get-invoice, preview-invoice, search-customers, or search-jobs. The field exclusions are noted, but there is no when-to-use or when-not-to-use context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context beyond annotations: it scopes results to the authenticated workspace, limits data to safe summary fields, and explicitly lists excluded fields. This is meaningful disclosure not present in the structured data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no filler. It front-loads the core purpose, then adds the key scoping constraint ('safe summary fields only') and a concrete exclusion list. Every phrase earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only search tool with seven optional parameters fully documented in the schema, the description covers purpose, auth scope, and return-data boundaries. It does not enumerate the exact safe summary fields or describe pagination/ordering, but the exclusions and annotations provide enough context for an agent to select and invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the input schema already documents all seven parameters with their meanings and constraints. The description does not add parameter-specific detail, but that is unnecessary here; a baseline of 3 is appropriate because the schema carries the semantic load.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('Searches the authenticated workspace jobs') and a precise resource, and it differentiates the tool from job-detail siblings by explicitly noting it returns only safe summary fields and excludes service addresses, notes, and amounts. This makes the tool's scope immediately understandable without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no explicit guidance on when to use this tool versus alternatives such as get-job or jobs-today. Although the exclusion of addresses, notes, and amounts implies it is not for full detail retrieval, there is no stated preference, prerequisite, or alternative routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the operation read-only and non-destructive; the description adds real behavioral context by scoping results to authorized workspace leads and explicitly excluding notes and estimated values. This tells the agent what to expect and what not to expect from responses, adding value beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One sentence delivers the action, scope, searchable fields, and a key exclusion without any filler. The core purpose is front-loaded, and every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With six optional but fully documented parameters, read-only annotations, and a clear field boundary, an agent has enough information to invoke the tool correctly. The absence of an output schema means the description could have said more about the exact return shape or matching semantics, but this is a minor gap for a bounded search.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the description does not need to explain the parameters. It does map the searchable fields (contact, source, status, service interest) onto the schema, but it adds no extra parameter-level meaning beyond what the input schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the verb ('Searches') and resource ('authorized workspace leads'), and adds useful scope limits: only contact, source, status, and service-interest fields are searchable, while notes and estimated values are excluded. It does not explicitly contrast with the get-lead sibling for retrieving a single lead, so it falls just short of a top score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is for lead searches within the authorized workspace and hints that it is inappropriate when notes or estimated values are needed. However, it gives no explicit guidance about when to prefer get-lead or another sibling, and it does not state when the bounded search is insufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is established. The description adds the workspace scoping constraint, which is useful context, but it does not disclose default status handling, pagination, or what 'physical' excludes. With annotations covering safety, a 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence with no filler. Every word earns its place, stating the action, resource, and scope efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple three-optional-parameter, read-only list tool with no output schema, the description plus annotations and schema is nearly complete. It could mention that query searches by location name and that status filters results, but the schema already covers those, so the minor gap does not significantly hinder an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 67% (query and status are described; limit is not), and the description itself adds no parameter detail beyond the schema. The schema's descriptions for query and status are adequate, and limit is inferable from its name and constraints, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Lists') and resource ('physical locations') and scopes it to 'the authenticated workspace,' which clearly distinguishes this from singular get-location and from report-oriented siblings. It does not explicitly mention the search/filter capability implied by the tool name, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus siblings like get-location, reports-by-location, or the many other search-* tools. It only states what it does, with no when/when-not or alternative routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark this as read-only and non-destructive, and the description adds a meaningful behavioral detail: internal cost and markup fields are deliberately not exposed. This is useful beyond the structured annotations and clarifies the data-access boundary.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The entire description is a single, information-dense sentence with no filler or repetition. It front-loads the action and resource, then adds the key boundary condition without unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple optional-parameter search tool with full schema coverage and safe read-only annotations, the description provides the essential scope and data-exposure boundary. It does not mention return behavior or pagination, but those are not critical given the schema's limit parameter and the absence of an output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all four parameters are already documented with their own descriptions and constraints. The description adds general context like 'active' and 'customer-facing' but does not add substantially new parameter-level meaning beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Searches') and identifies the exact resource: active customer-facing services and materials in the authenticated workspace. It also adds a distinguishing boundary by stating internal cost and markup fields are not exposed, which separates it from other search tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context that this is for searching customer-facing pricebook items in the authenticated workspace, implying it is appropriate for external/customer-facing use. It does not explicitly name alternatives or state when not to use it, but the scope is specific enough for most selection decisions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint and destructiveHint annotations already cover the safety profile, so the description does not need to restate that. It adds useful behavioral context by stating the search is limited to authorized estimates, bounded to specific fields, and will not search notes, terms, or addresses. This goes beyond what the schema and annotations alone provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no filler. It conveys the action, scope, searchable fields, and exclusions in one concise statement, which is easy for an agent to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only search tool with four well-documented parameters, annotations, and no output schema, the description provides enough information to invoke the tool correctly. It is slightly incomplete because it does not mention alternatives for retrieving a single quote by ID and leaves the 'total' reference ambiguous, but these are secondary gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3 even without parameter details in the description. The description adds the exclusion of notes/terms/addresses but does not enrich parameter understanding meaningfully. The phrase 'total fields' is slightly ambiguous because there is no total parameter in the input schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'searches' and the resource 'estimates' (quotes), which distinguishes it from sibling search tools like search-invoices or search-jobs. It also adds scope by saying only authorized estimates are searched and enumerates the bounded fields, so an agent can tell exactly what this tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context: use this tool to search authorized estimates by customer, status, title, and total fields, and it explicitly says notes, terms, and addresses are excluded. It does not name alternatives like get-quote or provide an explicit when-not-to-use branch, but the resource-specific wording is enough for an agent to route correctly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already communicate the read-only, non-destructive nature of the tool. The description adds the useful context that only 'authorized' campaigns are returned, which helps set agent expectations about access scoping. It does not disclose additional behavioral details like sorting or pagination beyond the schema's limit parameter.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no filler, front-loading the action and resource before listing filters. Every word contributes meaningful information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple, read-only search tool with three optional parameters and full schema coverage, the description plus schema is largely sufficient. A minor gap is the absence of a note about the return shape, but no output schema is provided and the search semantics are reasonably inferable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the parameters are already well documented in the schema. The description echoes the query parameter's coverage of name, channel, and job type, but adds no new semantics beyond what the schema already provides for limit, query, and status.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('searches') and resource ('authorized reactivation campaigns') and enumerates the filter dimensions: name, status, channel, and job type. This clearly differentiates the tool from sibling search tools like search-broadcast-campaigns and search-referral-campaigns.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool: when an agent needs to find reactivation campaigns by filters. However, it does not explicitly describe when not to use it or name alternatives such as preview-reactivation-campaign, leaving some routing to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds the 'authorized' scoping constraint, which is useful behavioral context beyond the annotations. However, 'bounded performance fields' is unexplained — it is unclear what performance metrics bound the results or how — and no match semantics (exact vs. fuzzy) are disclosed. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence of roughly fourteen words that front-loads the verb and resource before listing filter dimensions. Every word earns its place, and there is no repetition of annotation or schema content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple search tool with three optional parameters, full schema coverage, and no output schema, the description covers the essential scope and filter dimensions. Gaps include the unexplained 'bounded performance fields' and the absence of any hint about return format (a list of campaigns), but for such a simple read-only tool an agent can reasonably infer the result shape from the tool name and annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline 3 applies. The description lightly reinforces the query and status parameters by listing 'name, status, message channel,' but it introduces 'bounded performance fields,' which maps to no schema parameter, creating ambiguity about what additional filtering exists. The description adds marginal meaning beyond the schema but introduces one confusing term.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Searches') and resource ('referral campaigns') with clear scope qualifiers: 'authorized' and the filter dimensions 'name, status, message channel, and bounded performance fields.' The tool name and resource type cleanly distinguish it from sibling search tools such as search-broadcast-campaigns and search-reactivation-campaigns.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied through the resource type — an agent looking for referral campaigns would naturally select this tool. However, the description provides no explicit when-to-use guidance, no exclusions, and does not name alternatives like search-broadcast-campaigns or search-reactivation-campaigns for the other campaign types.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds value beyond annotations by disclosing that only 'authorized' reviews are searchable and that searches are restricted to 'bounded fields', which communicates scope constraints an agent should know.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded sentence with no filler. Every phrase contributes either the action, the resource, the searchable dimensions, or the boundary condition ('authorized', 'bounded fields').

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only, filterable search tool with 100% schema coverage and safety annotations, the description is mostly complete. The main remaining ambiguity is what 'bounded fields' means exactly, but the schema's query field description fills that gap adequately.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter is already documented. The description simply echoes the filter categories without adding format, combination rules, or behavioral notes beyond the schema, so it doesn't materially improve parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Searches') with a specific resource ('reviews') and enumerates the filter dimensions: reviewer, customer, job, rating, platform, and reply status. This clearly distinguishes search-reviews from sibling search tools like search-customers and search-jobs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly establishes the tool's role as finding authorized reviews by multiple criteria, giving the agent the context needed to choose it over other search_* siblings. It does not explicitly state when not to use it, but the resource-specific scope makes the intended use fairly unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish read-only, non-destructive behavior, so the bar is lower. The description adds valuable behavioral context beyond the annotations: results are scoped to the authenticated business, limited to active inbox records, and deliberately exclude descriptions, addresses, contact channels, and outreach controls.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no filler. It states the action, scope, and key exclusions efficiently, earning every word.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only search tool with optional parameters and strong annotations, the description covers scope, auth context, and data-redaction behavior well. Because there is no output schema, it could have pointed to get-service-request for retrieving full details, but 'bounded' plus the exclusion list gives adequate return expectations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and every parameter is already described in the schema. The description reinforces the default active-inbox scope but does not add meaningful new parameter-level semantics; this matches the baseline for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Finds'), a concrete resource ('active service-request inbox records'), and a precise scope ('for the authenticated business'). The phrase 'bounded' and the exclusion list clearly distinguish this search tool from singular retrieval tools like get-service-request.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use the tool: searching bounded, active service-request inbox records without exposing sensitive fields. It does not explicitly name alternative tools or state when not to use it, so it stops short of full routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds 'authorized' (implying permission constraints) and 'bounded content' (possibly indicating truncation or a limit), which is useful extra context. However, it does not elaborate on pagination, ordering, or how the bounded behavior is controlled, so it only partially extends beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no redundancy. It efficiently states the action and return fields. However, the term 'bounded' is vague and could be clarified, slightly reducing the score from 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 5 optional parameters, enums, and no output schema, so the description carries some burden. It lists the return fields, which aids the agent in understanding results, but leaves ambiguities like what 'bounded content' means, how to combine query parameters, and whether results are paginated. Given that the schema covers parameter details, the description is adequate but not complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all five parameters (limit, query, status, platform, review_id) are already documented in the schema. The description adds minimal semantic value by mentioning 'source-review' and 'approval', which map to review_id and status, but does not clarify the 'bounded' term or how the parameters interact. Baseline of 3 is appropriate given full schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Searches' and the resource 'authorized social drafts', and enumerates the return fields ('bounded content, status, platform, source-review, and approval metadata'). This distinguishes it from generic search tools and from 'preview-social-draft' which focuses on a single draft, though it does not explicitly reference the sibling. It is specific and not a tautology, hence a 4.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. It does not say 'use this to find drafts, use preview-social-draft to view a specific draft' or mention any exclusions. The only usage context is implicit from the name, which is insufficient for differentiation among many search tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.