recurly

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

Annotations already flag destructiveHint=true, and the description goes further by explaining billing behavior: the subscription remains active until term_end by default, and bill_date shifts the effective date to the next bill date. It also explicitly says 'This changes billing state,' adding useful behavioral context beyond the 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?

Three concise sentences with no filler. The core action and default behavior are front-loaded, the special-case parameter usage is explained in the second sentence, and the endpoint reference is a useful appendix. 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 simple two-parameter mutation tool with destructiveHint already annotated and full schema coverage, the description covers the essential behavior and effective-date semantics. It does not explain consequences like reactivation or whether cancellation can be undone, but those are not required for calling 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 coverage is 100%, so the schema already documents both parameters. The description adds meaningful context by spelling out the default timeframe behavior and what bill_date does, but this largely restates the schema's enum description for timeframe. It does not introduce entirely new parameter semantics.

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: 'Cancel a subscription.' It clearly distinguishes cancellation from the sibling recurly_pause_subscription by stating that cancellation changes billing state and takes effect either at term end or next bill date. The title also reinforces the write nature.

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 explains when the cancellation takes effect and how to choose between timeframe options, which is key usage context. However, it does not explicitly contrast this tool with recurly_pause_subscription or list when cancellation is preferred over pausing, so alternative selection is left partly 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?

The readOnlyHint annotation already signals that this is a safe, non-mutating operation, so the bar is lower. The description adds useful context by documenting the id-without-prefix and code- prefix conventions and the underlying REST endpoint, but it does not disclose any further behavioral details such as error responses, pagination behavior, or field selection. This is acceptable but not enriched beyond the 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?

Two sentences carry all the necessary information with zero redundancy. The core action is front-loaded, the id formats are packed with examples, and the endpoint reference is separate and terse. 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 single-parameter read operation, the description covers the primary usage details: what it fetches, the accepted identifiers, and the underlying API call. The readOnly annotation covers the safety profile, and the schema fully documents the parameter. A minor omission is the absence of any mention of the response structure or not-found behavior, but for a simple GET-style tool this is not a significant 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 input schema already covers the lone account_id parameter with a description that matches the prefix convention, so schema coverage is 100%. The description reinforces that with concrete examples ('e28zov4fw0v2', 'code-bob') and the API path, but it does not add meaning beyond what the schema already provides. 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 begins with a specific verb and resource, 'Fetch one account by its id', and clarifies the two accepted identifier formats. It implicitly distinguishes this from the sibling list_accounts by specifying a single account fetch, and cites the exact Recurly API endpoint, leaving no ambiguity about the operation.

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 for when this tool applies (fetching a single account by id or code) and provides concrete examples of valid inputs. It does not explicitly name alternatives or state when not to use it, but the 'one account' framing makes the intended use clear in contrast to listing or subscription operations.

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 annotation readOnlyHint already indicates a safe read operation. The description adds meaningful context beyond that: the id format requirement (no prefix vs uuid-) and the underlying Recurly REST endpoint. No contradictions.

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 with no filler. The key id-format rule is front-loaded, and the endpoint reference is a helpful one-line addition.

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-only fetch, the description plus annotation and schema are sufficient. It covers what is fetched, how to identifier it, and the safety profile. No output schema means return-format details are not 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?

Schema description coverage is 100%, so the schema already documents the parameter semantics fully. The description restates the same id/uuid guidance and adds the REST path, but does not provide substantive new 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 states a specific verb and resource: "Fetch one subscription by its id or uuid." It clearly identifies what the tool does and distinguishes it from sibling tools like cancel, pause, or list subscriptions.

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 usage is implied: use this tool when you have a subscription id or uuid and want that single subscription. However, it does not explicitly contrast with alternatives like list_subscriptions or state 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?

readOnlyHint=true already conveys the non-mutating profile, lowering the bar for the description. The text adds two real behavioral details — cursor pagination and the canonical 'Recurly: GET /accounts' endpoint — but does not disclose rate limits or response-shape behavior. That lands it at mid-range for an annotated read 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?

Three short sentences with zero filler: purpose first, capabilities second, canonical endpoint last. 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 read-only list with 0 required params and a fully documented schema, the description covers the invocation essentials and even announces pagination and filtering. With no output schema present, a note on the return shape would make it fully 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 coverage is 100%, so all 8 optional parameters (sort, order, email, limit, begin_time, end_time, past_due, subscriber) already carry descriptions; the baseline is 3. The description's 'filtering' mention only echoes the schema's filter params and adds no format or syntax semantics.

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?

Names a specific verb and resource — 'List customer accounts on the site' — with an explicit scope. The plural accounts resource and the List verb distinguish it from recurly_get_account and from the list_invoices/list_plans/list_subscriptions siblings without needing to open 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 verb and sibling set make the use case inferable (enumerate accounts rather than fetch one), but no alternative tool is named and no when-not-to-use condition appears. This is implied usage, not explicit 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?

The annotations already mark readOnlyHint as true, so the description only needs to add behavioral context. It adds the useful scoping detail ('across the site, or for one account') and the exact GET endpoints, but it does not describe pagination behavior, response shape, or any operational caveats. This is consistent with the annotation, not contradictory.

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 short sentences with no fluff. The core action and main scoping behavior are front-loaded, and the endpoint reference is useful without bloating. Every piece of text 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 list operation with 100% schema coverage and no required parameters, the description provides enough context: the action, scoping options, and endpoints. The lack of an output schema is mitigated by the predictable list semantics and the algorithm's existing Recurly API knowledge.

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 descriptions already carry the full meaning for sort, type, limit, order, state, time bounds, and account_id. The description only re-itirates the account_id scoping concept already present in the schema, adding no new parameter semantics.

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 begins with a specific action and resource ('List invoices'), then immediately clarifies the scope: across the site or for one account when account_id is given. It also cites the Recurly endpoints, making the operation unambiguous and clearly distinguishing it from sibling tools that list accounts, plans, or subscriptions.

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 for the two usage modes: site-wide listing vs. account-scoped listing triggered by account_id. It does not explicitly name alternative tools or state when not to use this tool, but the siblings are distinct resources, so confusion is unlikely.

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 annotation already establishes the read-only safety profile. The description adds that this maps to 'GET /plans' and supports an optional state filter, which is useful context. However, it does not disclose return format, pagination behavior, or any operational caveats beyond the annotation and schema.

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 primary purpose and then provides the API endpoint mapping. There is no filler, redundancy, or unnecessary explanation.

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 operation with six parameters all described in the schema, the description plus schema is sufficient for an agent to select and invoke the tool correctly. The lack of an output schema means return-value details are not specified, but the operation's purpose is clear enough that this is a minor gap rather than a blocking omission.

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 six parameters are already fully documented in the input schema. The description's mention of 'optionally filtered by state' simply echoes the existing 'state' parameter, adding no new semantic meaning beyond the structured 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 ('List'), a concrete resource ('the site's subscription plans'), and an additional dimension ('optionally filtered by state'). It is immediately distinct from sibling tools like recurly_list_accounts, recurly_list_invoices, and recurly_list_subscriptions because it names 'plans' 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 context signals show this is the only tool for listing plans among the siblings, so the intended use case is clear: call this when you need subscription plans rather than accounts, invoices, or subscriptions. It does not explicitly state when not to use the tool or name alternatives, but the resource naming provides sufficient contextual 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 readOnlyHint=true already covering the safety profile, the description adds useful behavioral context beyond the annotation: the endpoint selection behavior and the site-wide default scope. It stops short of describing pagination/response shape, but that is not critical for a read-only list 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?

Two tight sentences carry the full message: the first states purpose and scope, the second states the account_id endpoint condition. No filler, and the most important information is 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 tool with seven optional parameters, all covered by the schema, and a readOnly annotation, the description explains the one non-obvious behavioral choice (account-scoped vs site-wide endpoint) and leaves parameter details to the schema. The absence of an output schema is acceptable because the list semantics make the return shape predictable.

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 extra value by explaining that account_id changes the API endpoint and that state filtering is available, which goes beyond the individual parameter descriptions.

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 ('List') and resource ('subscriptions'), and immediately characterizes scope ('across the site, optionally scoped to one account and/or filtered by state'). This clearly distinguishes it from single-subscription get_subscription and mutating cancel/pause 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?

It gives direct conditional routing guidance: provide account_id to hit GET /accounts/{account_id}/subscriptions, otherwise GET /subscriptions, and state can be used as a filter. This is clear context for when to use the tool, though it does not explicitly contrast with sibling tools like get_subscription.

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 claim destructiveHint, and the description reinforces this by stating 'This changes billing state.' It also adds the meaningful resume/cancel-on-zero behavior without contradicting the 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?

Three concise sentences carry real load: the action, the special parameter semantics, and the underlying API endpoint. 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 low-complexity write operation with two well-documented required params and a destructive annotation, the description covers the behavior and the key edge case. It omits return-value or permission detail, but the ansent can invoke it correctly from this description.

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 both parameters at 100% coverage, so the baseline is a 3. The description adds extra value by explaining that remaining_pause_cycles=0 resumes/cancels an existing pause, which is not fully captured by the schema alone.

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?

States a specific action: pause a subscription for a defined number of billing cycles. The endpoint reference and the resume semantics distinguish it clearly from recurly_cancel_subscription.

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, especially the conditional behavior of setting remaining_pause_cycles to 0 to resume/cancel an existing pause. It does not explicitly point to recurly_cancel_subscription for permanent cancellation, but the contrast is implied by the tool name.

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