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

With no annotations provided, the description carries the behavioral burden. It usefully discloses that Sherweb exposes charges only as a billing-period collection, so the tool must read the period and select the matching charge. This non-obvious workaround is exactly the kind of behavioral context agents need. It does not discuss rate limits or auth, but 'Get full detail' makes the read-only nature reasonably clear.

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 filler. The primary purpose is front-loaded, and the second sentence explains a crucial behavioral constraint without unnecessary detail.

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?

Although there is no output schema or annotation context, this is a simple two-parameter lookup. The description explains the key billing-period behavior and the schema handles parameter guidance. It is complete enough for an agent to call the tool correctly, though a brief note on what fields 'full detail' contains would make it even stronger.

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; the schema already documents both parameters well, including the 'Use this when the charge falls outside the current period' guidance for the date parameter. The description adds context by explaining why the period is needed, but it does not add substantial new per-parameter 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 clearly states the action ('Get the full detail of one charge') and the resource ('charge by its ID'). It distinguishes itself from the sibling list tool 'sherweb_billing_payable_charges' by focusing on a single charge's full detail rather than a collection, though it does not explicitly name or contrast that sibling.

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 you need one specific charge's details by ID. The date parameter schema adds useful guidance for charges outside the current period, but the description itself does not explicitly state alternatives, exclusions, or when to prefer a sibling tool like the payable charges list.

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 behavioral disclosure burden. It clearly signals a read-only listing action ('Get ... Returns every charge') and enumerates the returned data categories (pricing, deductions, fees, taxes, invoice details). It does not mention pagination or auth requirements, but the tool is a simple read operation.

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, front-loaded with the primary action, and every clause adds useful detail about what is returned. There is no repetition 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 one-optional-parameter read tool, the description covers period selection and return contents comprehensively. It could be slightly more complete by naming the related charge-details sibling, but nothing needed to invoke 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 description coverage is 100%: the date parameter already includes format, UTC default, and an example. The tool description adds nothing beyond 'billing period', so it correctly relies on the schema rather than compensating for missing parameter documentation.

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 ('Get the distributor payable charges') and clarifies the scope ('every charge in the period — recurring, usage and setup'), which separates it from the sibling billing charge-details tool. It does not explicitly name an alternative, so it stops short of the strongest possible sibling differentiation.

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 usage context: querying distributor payable charges for a billing period. However, it gives no explicit when-to-use versus when-not-to-use guidance relative to siblings such as sherweb_billing_charge_details or accounts receivable.

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 present, so the description carries the behavioral burden. It usefully discloses that catalogs are per-customer and no global list exists, but it does not explicitly state that the operation is read-only or mention any limits or pagination behavior. For a simple list operation this is adequate but not deeply transparent.

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 concise sentences. The first names the verb, resource, and output fields; the second adds the critical per-customer constraint. 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?

The description lists the returned fields and the customer-specific nature of the catalog, which is the core information needed since there is no output schema. It omits only minor details like explicit read-only confirmation or pagination, which are not critical for this simple list 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?

Schema description coverage is 100%, so the baseline is 3 and the description adds no additional parameter-level meaning. The customerId and search semantics are already fully documented in 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?

Clearly identifies the tool as 'List the products a specific customer can be sold' and enumerates the output fields (SKU, localized name/description, billing cycle, commitment term). The per-customer boundary distinguishes it from billing and subscription sibling tools, so an agent can select it unambiguously.

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?

States clear context: catalogs are per-customer and there is no global product list, so a customer ID is required and this tool is for browsing what that customer can be sold. It doesn't explicitly name alternative tools, but the per-customer scoping makes the intended use apparent among siblings like subscriptions_list.

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 behavioral burden. It clearly indicates a read operation ('Get') and describes the returned information: receivable charges with cost, quantity, and currency. It does not cover pagination or error behavior, but for a straightforward read tool the disclosure is sufficient.

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, information-dense sentence with no filler. It front-loads the main purpose and includes only meaningful details about charge types and returned 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 simple two-parameter read tool without an output schema, the description provides enough context: the operation, the billing-period scope, and the return fields. It could be more complete by explicitly contrasting with payable charges or charge details, but it is not materially incomplete.

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 both customerId and date. The description reinforces the billing-period concept but does not add new parameter-level meaning beyond what the schema provides, matching the baseline.

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 ('Get') and names the exact resource: receivable charges billed to a customer for a billing period. It further specifies charge categories (recurring, usage, setup) and key attributes (cost, quantity, currency), making it easy to distinguish from sibling billing tools like payable charges.

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 'charges you bill a customer' provides clear context that this tool is for customer receivables, implicitly contrasting with payable/charge-detail siblings. However, it does not explicitly name alternatives or state when not to use this tool, so it falls just 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?

With no annotations, the description must disclose behavior, and it does reveal a meaningful non-obvious trait: Sherweb has no direct get endpoint, so this tool reads the whole collection and selects the match. However, it does not cover failure behavior, return format, or whether additional processing or errors should be expected.

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 short sentences, with the core purpose first and a valuable implementation note second. 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 single-parameter read tool, the description covers what the tool does and why it works through the collection. It does not describe the return value or not-found behavior, but no output schema exists and the overall complexity is low enough that these are moderate, not critical, 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 coverage is 100%, with customerId already documented as the customer's unique UUID. The description's 'by ID' wording only restates this, adding no new parameter semantics beyond what the schema 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 is a specific verb+resource statement: 'Get one customer by ID.' It also distinguishes this from the sibling list tool by using 'one ... by ID' and explains that Sherweb only exposes customers as a collection, so the tool selects from that list.

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 'by ID' implies the tool should be used when a single customer identifier is known, but it never explicitly names the alternative list tool or says when to prefer it. Usage guidance is therefore conveyed by implication rather than explicit when/when-not direction.

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 for behavioral disclosure. It states that the tool returns a list of customers with specific fields, which implies a read-only operation, but it does not explicitly disclose that it is non-destructive or mention any potential side effects, limitations, or pagination behavior. This is adequate but leaves some room for detail.

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, succinct sentence that immediately conveys the action and the resource. It includes all essential information about the returned fields without any fluff or repetition, making it efficiently front-loaded and easy to parse.

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 operation with a single optional parameter, the description is complete: it states what the tool does, who it applies to (service provider account), and what data is returned. No output schema exists, so the description adequately specifies the return fields, and there are no missing details that would hinder an agent from invoking 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 schema description coverage is 100% and already fully documents the 'search' parameter, including its optionality and local application. The tool description does not add any additional meaning or context about the parameter, so it remains at the baseline score for this dimension.

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 'List' and clearly identifies the resource: customers under the service provider account. It enumerates the returned fields (display name, ID, hierarchy path, suspension state, company contact info), which precisely distinguishes it from related tools like sherweb_customers_get (which likely fetches a single customer) and other billing 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 clearly indicates the tool is for listing all customers, providing context for when to use it. However, it does not explicitly exclude alternatives or mention when to use a sibling like sherweb_customers_get. This falls short of an explicit 'when/when-not' but is clear enough for an agent to infer the intended use.

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?

Since no annotations are provided, the description carries the behavioral disclosure burden. It clearly indicates the tool only returns tool names and descriptions, is non-mutating, and requires no prerequisite. More detail on output format would improve it, but the description is adequate for a simple discovery 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 two concise sentences with the purpose front-loaded and the non-prerequisite caveat included. Every sentence 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 one-parameter discovery tool, the description and rich schema provide enough context to select and invoke it correctly. The only minor gap is a more detailed output shape, but the description already states that tool names and descriptions are 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 each enum value has a clear, meaningful explanation. The description itself adds no extra parameter semantics beyond saying the tool is domain-based, 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 ('Discover') and identifies the resource ('available Sherweb tools by domain'). It also states what it returns ('tool names and descriptions') and distinguishes itself from operational siblings by positioning itself as a discovery aid.

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 explicitly states that this is a help/discovery aid and not a prerequisite, clarifying when not to call it. It does not name alternative sibling tools, but the domain enum in the schema provides clear domain 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description is minimal and doesn't explain what 'credentials status' reports (valid/invalid, expiry), whether it makes network calls, whether it requires prior authentication setup, or what a failure looks like. For a status-checking tool with zero annotation coverage, this is underspecified.

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 efficient sentence with no wasted words. It's appropriately concise for a tool with zero parameters. However, it could have used the brevity freedom to add behavioral context without bloating.

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 zero parameters and a simple purpose, the tool operates within a 10-tool Sherweb ecosystem. The description doesn't explain what the output looks like (no output schema), what 'credentials status' means in practice, how 'available domains' relates to other tools, or when a user would want this information. For a status tool that likely serves as a pre-flight check for the rest of the API tools, more context would materially help 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 tool has 0 parameters and 100% schema description coverage (an empty schema is trivially fully covered). With no parameters, the description has no parameter semantics responsibility. The description accurately reflects that it takes no inputs, so a baseline 4 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 'Show credentials status and available domains' states a clear action ('show') with a specific resource (credentials status and available domains). However, it doesn't distinguish itself from the sibling tools like sherweb_navigate or the various list/get tools, and 'credentials status' is somewhat vague about whether these are API credentials, user credentials, or something else.

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 on when to use this tool versus its siblings. There's no mention of whether it should be called first to verify credentials, to discover available domains before other operations, or any other contextual usage direction. With 10 sibling tools, this lack of usage guidance is a notable gap.

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 behavioral disclosure burden. It reveals the full set of return states (Unknown, Queued, Processing, Success, Failure), clarifying that the tool is a read-only status poll rather than a mutating operation. It could add error-handling details, but for a status-check tool this is solid disclosure.

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, no filler, and the essential action is front-loaded. The return-value list is compact and directly useful, and the reference to the sibling submission tool is placed where it is most helpful.

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 covers what the tool does, how to get the input, and what the outcome will be. It does not discuss error handling or polling semantics, but those are not necessary for an agent to invoke the tool successfully in most cases.

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 baseline is 3. The description adds value by explaining that the trackingId comes from sherweb_subscriptions_change_quantity, giving the agent provenance and reducing ambiguity about how to obtain the valid input. This goes beyond the schema's simple 'returned when the amendment was submitted'.

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 resource ('submitted subscription amendment'), a specific action ('Check the status'), and a required input ('tracking ID'). It directly distinguishes itself from sibling tools like sherweb_subscriptions_change_quantity by focusing on status retrieval rather than submission.

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 clearly indicates the tool is used after an amendment is submitted, and explicitly points to sherweb_subscriptions_change_quantity as the source of the tracking ID. It does not explicitly state when not to use it, but the context is so specific that an agent can easily infer appropriate usage.

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 behavioral burden. It discloses that the operation 'affects billing', is 'submitted asynchronously', and returns a tracking ID rather than a completed result. These are significant behavioral details beyond what the input schema conveys.

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 and front-loaded: the first sentence states the operation, and the second packs billing impact, async behavior, and the polling pointer. There is no filler, repetition of schema fields, or unnecessary detail.

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 lacking annotations and an output schema, the description gives the agent the key operational facts: what is changed, the billing side effect, the async submission model, and the exact status tool to poll. For a simple three-parameter mutation, this is sufficiently 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 the parameter names and descriptions already explain quantity, customerId, and subscriptionId. The description adds only 'seats/licenses' clarification and billing impact, but does not meaningfully extend the parameter semantics beyond the schema. 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 opens with a specific verb-resource pair: 'Change a subscription's quantity (seats/licenses)', not a generic 'process' or 'update'. It also distinguishes itself from siblings by referencing sherweb_subscriptions_amendment_status, making clear this tool does not return a finished result.

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 explicitly states when to use this tool: to change a subscription quantity. It also names the follow-up tool to poll, sherweb_subscriptions_amendment_status, and contrasts it by saying the change is 'not a finished result', guiding the agent away from expecting completion here.

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 burden. It discloses a non-obvious implementation detail: the tool reads a customer's subscription details and selects the matching subscription, which helps an agent understand the per-customer scoping. It does not mention error behavior or return format, but for a read operation this is still above average.

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 tight sentences with no filler. The primary purpose is front-loaded, and the second sentence earns its place by explaining the API constraint that is essential for correct invocation.

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 operation, the description is largely complete: it states what the tool does, the required pairing of IDs, and the non-obvious per-customer behavior. It could be slightly stronger by explicitly naming the list tool as the enumeration path, but nothing critical is missing for a correct call.

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 fully documents both UUID parameters, so the baseline is 3. The description adds meaning beyond the schema by explaining why both IDs are required and how they relate: subscriptions are only exposed per customer, and the tool selects the match from that customer's subscription list.

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 ('Get') and resource ('one subscription's full details'), clearly signaling a singular lookup. The singular scope distinguishes it from sherweb_subscriptions_list, and the phrase 'full details' makes the intent unambiguous.

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 conveys an important usage constraint: Sherweb exposes subscriptions only per customer, so both customerId and subscriptionId are needed. However, it does not explicitly say when to use this tool instead of sherweb_subscriptions_list or that the list tool should be used first for enumeration.

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 bears the full burden of behavioral disclosure. It usefully states the returned attributes, which clarifies the output content, but it does not mention pagination, limits, ordering, authorization requirements, or error 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, front-loaded sentence that states the action, scope, and returned fields with no filler. 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 simple one-parameter list operation with no output schema, the description is largely complete: it states what is listed and which fields are returned. The main gap is lack of pagination or result-limit information, but this does not prevent 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?

The schema fully documents the single parameter (customerId as a UUID), so schema coverage is 100%. The description adds only the implicit context that subscriptions belong to a customer, which aligns with the parameter but does not meaningfully extend its semantic 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 uses a specific verb ('List') and resource ('a customer's subscriptions'), and enumerates the returned fields: product name, SKU, quantity, billing cycle, purchase date, fees, and commitment term. It is clear in intent, though it does not explicitly differentiate from sibling sherweb_subscriptions_get by naming it.

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 used when you need all subscriptions for a specific customer, with the customerId required. However, it provides no explicit guidance about when not to use it or when to prefer siblings such as sherweb_subscriptions_get.

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