drefinery

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

With no annotations present, the description carries the full burden of behavioral disclosure. It indicates this is a read-only lookup, but it does not disclose what happens when no match is found, whether coverage is limited to 'verified' tools only, or how current the data is. For a simple lookup tool, this is a moderate 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?

The description is a single, front-loaded sentence with no filler. Every word contributes to conveying the tool's purpose and content, making it highly efficient.

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 lists the types of data returned (pricing tiers, feature checklists, token costs, overage rates), which is helpful given there is no output schema. However, it does not explain output format, limitations, or how this tool differs from the closely named custom pricing matrix sibling, leaving the agent with some ambiguity about scope and alternatives.

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 fully documents both 'category' and 'companyOrProduct'. The description adds no new parameter-level detail, but does not need to; it stays at the baseline 3.

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 ('Lookup') and resource ('verified, structured pricing tiers... for B2B SaaS/AI tools'), clearly stating what the tool does and what kind of data it returns. However, it does not explicitly distinguish itself from the similarly named sibling 'refinery_custom_b2b_saas_pricing_matrix', so the uniqueness is somewhat ambiguous without further inspection.

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 a general sense of when to use the tool (when you need B2B SaaS/AI pricing data), but it provides no explicit guidance on when to use this tool versus the custom pricing matrix sibling, nor does it mention any exclusions or alternatives. There is no 'when-not-to-use' information.

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?

No annotations are provided, so the description must carry the transparency burden. It explains that the tool extracts normalized costs, seat limits, quotas, and overage terms, which conveys a read-only extraction behavior. However, it does not mention failure modes, access constraints, rate limits, or how the extracted data is returned.

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 worded sentence with no filler. The '[Custom Enterprise Schema]' marker is front-loaded, and every phrase contributes useful 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 one-parameter extraction tool, the core input and output dimensions are named, which is adequate. But with no output schema and no annotations, there is still a gap around expected response shape, limitations, and how this tool relates to the sibling pricing-matrix tool.

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, url, is already well documented by the input schema ('Target URL to ingest and distill'), and schema coverage is 100%. The description adds domain context but does not materially expand the meaning of the url parameter itself.

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 verb ('Extracts') and a concrete resource: normalized pricing, quota, and overage data for SaaS vendors. It is specific enough to convey the tool's purpose, but it does not explicitly distinguish itself from the near sibling refinery_b2b_pricing_matrix beyond the '[Custom Enterprise Schema]' tag and 'SaaS' qualifier.

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 'across SaaS vendors' implies when this tool is relevant, but there is no explicit 'use this when' guidance, no exclusions, and no direction about choosing between this and refinery_b2b_pricing_matrix. An agent must infer the intended use case.

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 no annotations, the description carries the full burden of behavioral disclosure. It states what data is extracted but does not disclose whether the operation is read-only, whether authentication is needed, how failures or non-extractable content are handled, or how results are returned.

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 compact sentence with a concrete itemized list, making the key information quick to parse. The '[Custom Enterprise Schema]' prefix adds little value, but the rest is lean and front-loaded.

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 extraction tool, the description names the input and the main categories of output, enough for a basic call. However, with no output schema, no annotations, and no sibling differentiation, it leaves gaps around result shape, processing behavior, and selection among similar refinery tools.

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 fully documents the only parameter, url, as 'Target URL to ingest and distill' (100% schema coverage), so the baseline is 3. The description adds domain context but no additional URL format, constraints, or usage 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 names a specific verb ('Extracts') and a precise list of outputs: active chemical ingredients, FDA 510(k)/NDA approvals, clinical trial phases, black-box warnings, and patent exclusivity expiration dates. It clearly identifies the tool's domain and purpose, though it does not explicitly differentiate it from overlapping siblings such as refinery_custom_clinical_trials or refinery_regulatory_compliance.

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 guidance on when to choose this tool versus its siblings or when it is not appropriate. The agent is left to infer applicability from the data categories and the tool name rather than being given explicit conditions 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?

No annotations are provided, so the description must carry the full behavioral burden. It discloses that the tool extracts certain data from a URL, but it does not state whether the operation is read-only, whether it fetches the URL itself, what the output format is, whether authentication is needed, or how failures are handled. The phrase 'ingest and distill' in the schema hints at processing but does not clarify the tool's 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 concise sentence with no filler. It front-loads the core action and enumerates the extracted data types efficiently, which is appropriate for a one-parameter tool.

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 URL-to-extraction tool: it names the input and the extracted fields. However, with no output schema and no annotations, it lacks details about return structure, failure behavior, and how to choose between this and other refinery custom-schema tools, leaving meaningful gaps for 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?

The schema already covers the single parameter with 100% coverage: 'Target URL to ingest and distill.' The description adds context about what kinds of information will be extracted from the URL, which helps an agent understand what URL content is relevant, but it does not add constraints, format, or syntax details 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 specific verb ('Extracts') and a concrete resource ('clinical trial phases, target molecular biomarkers, primary endpoints, and enrollment criteria'), making the tool's function immediately clear. It also distinguishes itself from sibling tools like refinery_custom_biopharma_fda_patent_cliffs and refinery_custom_health_insurance_clinical_policy by targeting clinical trials specifically.

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 should be used when a URL needs to be turned into structured clinical-trial information. However, the description gives no explicit guidance on when to prefer this tool over siblings such as refinery_refine_custom_url or refinery_semantic_search, and no exclusion criteria are stated.

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 no annotations, the description carries the full burden of behavioral disclosure. It clearly reveals the types of output the tool produces, which is useful, but it does not mention limitations, output format, or any side effects. This is adequate but leaves clear gaps for an agent reasoning about 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, tightly-scoped sentence that front-loads the key behavioral outcome and lists concrete output categories. There is no filler, repetition, or unnecessary qualification.

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 only one parameter and no output schema, so the description's specification of extracted content types helps. However, it does not explain the response format, nor does it route the agent away from the similar generic breaking-changes sibling. It is workable but not complete on its own.

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 'url' parameter is already described as 'Target URL to ingest and distill'. The tool description does not add parameter-level detail beyond that, 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 states a specific action — 'Extracts deprecated functions, removed parameters, breaking signature shifts, and exact before/after code migration snippets' — with a clear resource and target audience. It is detailed enough to distinguish from more generic breaking-change tools, though it does not explicitly contrast itself with sibling 'refinery_dev_breaking_changes'.

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 about when to use this tool versus the related 'refinery_dev_breaking_changes' or other custom schema tools. The description implies usage for AI coding agents needing migration help, but it never states exclusions, prerequisites, or when a sibling is preferable.

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 no annotations provided, the description carries the full burden of explaining behavior, but it only says 'Structured clinical intelligence' and 'ingest and distill.' It does not reveal what the tool does with the URL, what kind of structured output is produced, whether any state is persisted, or what side effects may occur. This is far too little behavioral disclosure for an unannotated 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 concise sentence with no redundant wording. It is front-loaded with the '[Custom Enterprise Schema]' flag. However, its brevity sacrifices meaningful content, so it is concise in size but not in substance.

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?

Despite having only one parameter, the tool has no output schema, no annotations, and a description that does not specify what the 'distilled' result looks like. An agent cannot confidently determine what data will be returned, how the URL is processed, or how the output is structured. This is incomplete for practical 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 schema provides 100% coverage for the single 'url' parameter with the description 'Target URL to ingest and distill,' so the schema already explains the parameter adequately. The main description adds domain context ('pharmaceutical and biotherapeutic regulatory milestones') but no parameter-specific usage detail. Since schema coverage is high, a 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 is a vague, noun-phrase slogan: 'Structured clinical intelligence for pharmaceutical and biotherapeutic regulatory milestones.' It does not state a specific action like 'extract,' 'analyze,' or 'find drug approvals.' It also fails to differentiate from siblings such as refinery_custom_biopharma_fda_patent_cliffs or refinery_custom_clinical_trials, which could plausibly share the same description.

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 guidance on when to use this tool versus alternatives. No context is given about suitable input types, desired use cases, or exclusions. The only hint is the parameter description 'Target URL to ingest and distill,' which implies a fetch-and-extract workflow but does not explain when this tool is the right choice.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes outputs ('Extracts...') but does not state whether the tool is read-only, whether it requires authentication, whether it persists data, or what happens with invalid or unsupported URLs.

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 compact, front-loaded with the schema marker, and uses a single sentence to enumerate specific extracted entities. The '[Custom Enterprise Schema]' prefix is mildly redundant but not harmful.

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 lists key output categories, which is helpful given the absence of an output schema. However, it does not mention return format, URL requirements, error cases, or how structured the extracted data is, leaving some ambiguity for an agent preparing to invoke the tool.

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, url, is fully described by the schema ('Target URL to ingest and distill'), giving 100% schema coverage. The description adds context about the kind of information extracted but does not need to restate the parameter meaning.

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 ('Extracts') and a specific resource scope ('health plan claims', 'CPT procedure codes', 'drug formulary tiers'), making it immediately distinguishable from sibling tools like pricing matrices, patent cliffs, and zoning compliance 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 domain is obvious from the description and sibling names, so an agent can infer when to use this tool. However, there is no explicit guidance about when not to use it, what URL types are acceptable, or how it differs from the generic refinery_refine_custom_url tool.

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 no annotations, the description carries the full burden. 'Extracts' communicates a read-only operation and lists expected output subjects, which is useful. However, it does not disclose URL requirements, access limitations, result formatting, pagination, or failure behavior, so transparency is partial.

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 definition is one efficient sentence with no filler. It front-loads the extraction purpose and lists concrete outputs, earning 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?

For a one-parameter extractor with no output schema, the description is reasonably complete: it names the input and the output categories. It stops short of full completeness by not specifying what constitutes a valid target URL or how results are returned, but those are minor gaps for this simple tool.

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 documents the single url parameter as 'Target URL to ingest and distill', so the description adds no extra parameter-level meaning beyond the tool's broader purpose. Since schema description coverage is 100%, a 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 clear extraction verb and enumerates specific outputs: city zoning classifications, short-term rental permits, inspection checklists, and penalty fine structures. This makes the tool's purpose concrete and distinguishes it from generic sibling tools such as refinery_regulatory_compliance.

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 choose this tool over closely related siblings like refinery_custom_real_estate_zoning or refinery_regulatory_compliance. The description implies a use case but does not state prerequisites, exclusions, or alternatives.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It indicates that data is extracted from a URL but does not clarify whether the operation is read-only, how input URLs are processed, what happens on failure, or what the output format will be.

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 lists concrete extracted attributes. The '[Custom Enterprise Schema]' prefix is boilerplate and adds little value, but overall there is no meaningful waste.

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-URL extraction tool, the description is minimally adequate and names the key outputs. However, it fails to describe the return structure, any URL constraints, or why this tool should be chosen over refinery_custom_municipal_zoning_compliance.

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 provides 100% coverage for the single parameter, with 'Target URL to ingest and distill' already defining the 'url' property. The description adds field-level output context but no additional parameter-level meaning; baseline 3 applies since the schema already does the work.

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 clear verb ('Extracts') and names specific resources: property zoning categories, building square footage, permit approval status, and construction costs. However, it does not explicitly distinguish itself from the closely related sibling tool refinery_custom_municipal_zoning_compliance, which likely overlaps in purpose.

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 usage guidance is provided. The description does not state when to use this tool over alternatives, nor does it mention any exclusions or preferred scenarios. The presence of a similarly named zoning-compliance sibling makes this gap more significant.

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 no annotations, the description carries the behavioral transparency burden. 'Extracts' clearly signals a non-mutating analysis operation and 'from SEC filings' defines the input scope, but the description does not disclose output format, edge cases, or operational constraints. Since extraction is inherently read-only, the lack of side-effect disclosure is less critical than for mutation tools.

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, and the extracted-data list is precise and compact. The '[Custom Enterprise Schema]' prefix is minimal and does not add meaningful clutter.

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 tool with one parameter and no output schema, the description is largely complete: it names the input domain, the extraction action, and the output categories. It does not explicitly restrict the filing type to 10-K, though the tool name implies it, which 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?

The schema covers the URL parameter completely, so the baseline is 3. The description adds valuable domain semantics by specifying that the URL should point to an SEC filing and by naming the financial/risk items to be extracted. This goes beyond the schema's generic 'Target URL to ingest and distill'.

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 the specific verb 'Extracts' and names the exact resources and data types: GAAP vs non-GAAP operating metrics, total debt maturities, forward guidance, and risk factors from SEC filings. This clearly distinguishes it from sibling tools focused on pricing, clinical trials, zoning, and other 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 the tool is for SEC-filing analysis but does not explicitly state when to choose it over generic alternatives such as refinery_refine_custom_url or refinery_semantic_search. It provides no exclusions or comparative conditions.

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?

There are no annotations, so the description carries the behavioral disclosure burden. 'Query' implies a read-only operation, and the listed content types are helpful. However, it does not disclose response format, pagination, version-range handling, or any caveats about the returned 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 front-loaded sentence with no filler. Every clause contributes useful information about the tool's scope and content types.

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 insufficiently complete for an agent selecting among many refinery tools. It fails to disambiguate from refinery_custom_dev_sdk_breaking_changes, offers no usage context, and provides no indication of what the response looks like despite there being no 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%, and each parameter already has a clear description in the input schema. The tool description adds little semantic value 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 uses a specific verb ('Query') and names the resource clearly: refined developer changelogs, API deprecations, breaking changes, and migration code diffs for packages/APIs. It is easy to understand what the tool does, but it does not explicitly differentiate itself from the similarly named sibling tool refinery_custom_dev_sdk_breaking_changes.

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 about when to use this tool instead of alternative refinery tools. A near-identical sibling name exists, yet there is no mention of which scenarios favor this tool or when the sibling should be selected 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?

With no annotations provided, the description carries the full disclosure burden and does reveal a genuine pipeline: remote fetch, HTML/document cleaning, Workers AI extraction, and JSON verification — informative beyond the tool name. However, it omits edge behaviors such as failure on inaccessible URLs, document size/timeout limits, or what 'verified' actually entails.

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 21-word sentence that front-loads the core action and follows logical pipeline order (ingest → clean → extract → verify). Every clause earns its place; there is zero 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?

For a low-complexity tool (2 required params, no nested objects), the description covers input, process, and output in one compact statement. But with no output schema and no annotations, it leaves the exact JSON structure undefined and says nothing about failure modes or input constraints for a tool that accepts 'any arbitrary URL'.

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% — both url and instructionPrompt already have meaningful descriptions in the schema. The description's pipeline language ('structured extraction', 'verified JSON') loosely maps to instructionPrompt's role but adds no parameter-specific detail beyond what the schema already provides, 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 verb-resource pair ('Ingest any arbitrary URL') and a clear multi-step pipeline: clean HTML, run Workers AI structured extraction, return verified JSON. 'Any arbitrary URL' implicitly distinguishes this as the general-purpose tool against the domain-specific siblings (b2b pricing, clinical trials, zoning, etc.), though it never names that contrast explicitly.

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 'any arbitrary URL' implies this is the catch-all tool for URLs not covered by the specialized refinery siblings (pricing matrices, SEC 10-Ks, zoning, etc.). However, there is no explicit when-to-use vs. when-not-to-use statement, no named alternatives, and no exclusion criteria for documents the tool cannot handle.

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?

No annotations are provided, so the description carries the full behavioral burden. It names categories the tool 'checks' but does not disclose output format, coverage limitations, data source, recency, or whether results are summaries or raw documents. This is a meaningful transparency gap for a compliance 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 compact sentence with no filler or repetition. It front-loads the action and then efficiently enumerates the tool's coverage areas, making every part informative.

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 and schema cover what the tool does and its two parameters, but there is no output schema and no guidance on what a returned compliance check looks like or how the optional parameters should be combined. For a simple two-parameter tool this is adequate but leaves notable 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 both parameters are already documented in the input schema. The description adds general context about the domain but no additional parameter-level meaning beyond what the schema provides, 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 a specific action ('Check') and a defined resource ('municipal, state, and federal regulatory rules, required permits, compliance deadlines, and grant requirements'). It is distinguishable from zoning-focused siblings by emphasizing broad regulatory scope plus permits, deadlines, and grants, though it does not explicitly name or contrast those 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 gives no guidance on when to choose this tool over siblings like refinery_custom_municipal_zoning_compliance or refinery_custom_real_estate_zoning. It implies regulatory compliance questions are in scope but provides no exclusions, prerequisites, 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?

With no annotations, the description carries the full burden for behavioral disclosure. It communicates the search mechanism ('semantic search') and scope ('all refined knowledge databases'), which implies a read-only operation, but it does not explicitly confirm non-mutation, return characteristics, or limitations like rate limits or filtering 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 concise sentence that front-loads the action and scope. It loses a point because 'edge vector' is unexplained jargon that may reduce clarity for an agent.

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 tool with three parameters, no annotations, and no output schema, the description is too sparse to be complete. It does not explain the result format, the meaning and behavior of topK and domain, or how this general semantic search relates to the twelve sibling tools, so an agent has to make several assumptions before calling 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?

Schema description coverage is only 33%, and the description adds no parameter-level meaning beyond what the schema already exposes. topK and domain, including the domain enum values, are left for the agent to infer from names and defaults; the description does not explain how 'all refined knowledge databases' maps to the domain 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 uses a specific verb and resource ('Perform edge vector semantic search') and defines the scope ('across all refined knowledge databases'), so an agent can tell it is a general retrieval tool rather than a domain-specific sibling. It is distinguishable from the sibling tools by the word 'all', but the jargon term 'edge vector' is unexplained and slightly obscures the meaning.

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 'across all refined knowledge databases' implies this is the broad search tool, and the sibling names suggest narrower domain-specific alternatives. However, the description never explicitly states when to choose this tool over a specific refinery_* tool 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.