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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), and the description usefully adds the backing endpoint (GET /aggregates/case-status), the deprecation of the 'pending' status, and the 403 behavior when cases are not enabled for a team. That is genuine operational context beyond structured fields, though no rate-limit or pagination detail is given.

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 sentences, front-loaded with the core purpose followed by optional scoping and an edge-case note; nothing is repetitive. The long parenthetical status list and filter enumeration make it dense, but each clause carries information an agent needs.

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?

There is no output schema, so the description must convey the return shape, and 'how many cases are in each status' does so adequately for a count-by-status aggregate. Combined with the 403 caveat and status vocabulary, an agent has enough to call and interpret it, though the exact response structure is not spelled out.

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

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

With 100% schema description coverage, the schema already documents all four parameters, including the assigned_to=false meaning for unassigned and the date precision rules. The description largely restates those filters; its only added semantic is that 'pending' is deprecated, which is modest value.

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 aggregation verb and resource ('How many cases are in each status') and enumerates the exact status vocabulary, so an agent knows this returns counts, not a case list. It is clearly distinguishable from siblings like list_records or get_check, which return entities rather than aggregates.

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 spells out the optional scoping dimensions (single assignee, unassigned, status-update date range, active vs archived), which implicitly tells the agent when this tool applies. It does not, however, name an alternative or state when not to use it, so it stops short of full routing guidance.

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

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial beyond that: the endpoint used (GET /checks/{id}?expand=response), beta status of responses, type-specific availability, and exactly which sensitive fields appear only with include_contact_details while images/selfie/PDF are never 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?

It is a single dense paragraph that front-loads the purpose and then layers endpoint, beta caveat, and privacy behavior. Every clause carries information, though the run-on structure and heavy parentheticals could be broken up for easier scanning.

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

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

With no output schema, the description fully carries the burden of describing return shape (type, status, response, per-report status/result, verification breakdown) and data-access caveats, so an agent knows what it will receive.

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 both parameters are already documented, and the description's mention of include_contact_details largely mirrors the schema text. The privacy framing adds mild value but no syntax or format detail beyond the schema, so the baseline 3 applies.

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

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

The description names the resource ('one check by ID'), its origin ('from a record's check steps'), and the payload returned (type, status, response with per-report status/result and verification breakdown). This clearly separates it from siblings like get_record or get_client.

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 establishes the context that check IDs come from a record's check steps, implying get_record precedes this call, and notes that responses are beta so other check types may return 'not yet available'. It lacks an explicit when-not or named alternative, but the usage context is clear.

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

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

Annotations already cover readOnly, idempotent, non-destructive and openWorld, so the safety profile is done. The description adds genuinely useful context beyond that: the underlying endpoint (GET /clients/{id}) and, importantly, that sensitive PII (email, landline, mobile, DOB, NIN) is withheld unless include_contact_details is set. It does not say what happens for an unknown ID.

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 tight sentences, front-loaded with the core purpose and ending on the parameter caveat. The field enumeration is information-dense rather than padding, and nothing is wasted.

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

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

With no output schema, the description carries the burden of describing the return shape, and it does so adequately by listing the returned fields. For a simple two-parameter read tool with strong annotations this is nearly complete; only error behavior for a missing/invalid ID is unaddressed.

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 fully documented in the schema, including the exact fields gated by include_contact_details. The description restates that the contact fields are conditional but adds no format, range, or default nuance beyond the schema, so the baseline 3 applies.

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

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

States a specific verb and resource (fetch one client by ID) and enumerates the returned fields (name, decision status, reference, archived flag, retention date, timestamps), so the agent knows exactly what it gets. It separates itself from list_clients by the singular 'One client by ID', though it never names that sibling 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?

Usage is implied rather than stated: you need a known client_id and want a single client rather than a list. The description does give real conditional guidance for include_contact_details ('only with'), which is the closest thing to explicit when-to-use. It offers no exclusions or named 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?

Annotations cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower; the description nonetheless adds real behavioral content — the two underlying API calls, default expansion, and the significant redaction behavior (emails, phone numbers, dates, postcodes, NI/NHS numbers) that changes only with include_contact_details. It does not mention pagination or latency cost of the extra call.

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?

Front-loaded with the core purpose, then progressively discloses mechanics. Dense but nearly every clause carries information (the status enum list, the alternative routing, the redaction trigger). Slightly overlong in the embedded API path 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?

With no output schema, the description does the work of describing the return shape (steps with check status and latest review). It covers the main toggles and the routing to get_check, leaving only minor gaps like error behavior for missing IDs.

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

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

Schema description coverage is 100%, and the schema already documents all three parameters thoroughly, including defaults. The description restates the default expansion and the contact-detail/de-redaction effect, which reinforces but adds little syntax or edge-case 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?

States a specific verb and resource ('One record by ID with its steps') and immediately scopes it against siblings by explaining what the default expansion yields. An agent can distinguish this from list_records and get_check without opening any 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?

Names the alternative explicitly ('Use get_check for a result breakdown'), which routes the agent away from this tool for detailed check analysis. It lacks an explicit when-not-to-use statement for the collection-level siblings (list_records), but the context is clear.

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

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds the GET endpoint and notes that contact email and perform URL appear only with include_contact_details, but the redaction semantics it gestures at are already spelled out in the schema, so net new behavioral insight is modest.

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 compact sentences: what it returns, the endpoint, and the one opt-in caveat. Front-loaded with the resource, no filler, though the raw endpoint string is of limited value to 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?

With no output schema, the description usefully sketches the return shape (status, contained steps with type/completion/cost/IDs, dates) and flags the redaction toggle. Pagination mechanics live in the schema, so coverage is adequate for a read-only 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 schema already documents page, max_results, client_id and include_contact_details in detail. The description only re-summarizes the include_contact_details effect (contact email, perform URL) without adding syntax or defaults beyond the schema; baseline 3 applies.

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

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

States a specific resource ('every record / onboarding request sent to one client') and enumerates the returned fields, so the agent knows it's the per-client variant. It doesn't explicitly name the sibling list_records, but the 'one client' scoping implicitly differentiates 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?

Usage is implied by the scoping phrase 'sent to one client' — use it when you have a client_id. There is no explicit when-to-use/when-not or reference to list_records as the alternative for unscoped record listing, so the agent must infer the boundary.

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

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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint, so the safety profile is covered. The description adds genuinely useful disclosure not in the annotations: contact data (emails, phones, DOB, NI numbers) is gated behind include_contact_details and otherwise redacted, and it names the underlying endpoint GET /clients. It doesn't discuss paging behavior in prose (that lives in max_results), which keeps it below a 5.

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 sentences, zero filler, front-loaded with what a client is and what is returned, then filters, then the sensitive-data caveat. The middle filter sentence is dense but each clause maps to a real parameter.

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

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

With no output schema, the description usefully enumerates returned fields and the sensitive-data gate, which is the main completeness burden for an 11-param list tool. Pagination semantics and continuation via next_page are left entirely to the schema, so the definition is near-complete rather than fully self-contained.

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

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

Schema description coverage is 100% with 11 well-documented parameters, so the schema does the heavy lifting and the baseline of 3 applies. The prose recap of the filter surface adds confirmation but no syntax or format detail beyond the schema, and its 'sort by name or date' phrasing is looser than the schema's six-value sort_by enum.

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 the verb (list) and resource (clients) and disambiguates the resource with the parenthetical 'the people being onboarded', which separates it from list_records and list_client_records. It also enumerates the returned fields (name, decision status, reference, retention date, timestamps), so an agent knows exactly what this collection contains.

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 states the usable filter and sort surface (fuzzy search, status, visibility, assignee, exact reference, deletion-date bucket, sort order), which tells the agent when this tool can answer a query. It stops short of naming the single-client alternative (get_client) or the condition that selects it, so it reads as strong context without explicit routing.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds the underlying endpoint (GET /records) and hints at cross-team scope, but says nothing about pagination behavior, rate limits, auth requirements, or how the default redaction of contact data interacts with list output.

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 compact sentences, front-loaded with what the tool returns before moving to filters/sorting and then the endpoint. Every sentence carries information, though the endpoint mention is marginally useful to an agent that never sees HTTP directly.

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

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

With no output schema, the description does the work of summarizing record contents (status, client name/ID, steps, dates) and enumerating filter/sort axes, which is enough for correct invocation. The main omission is routing guidance against the record-related siblings, plus pagination expectations.

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

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

Schema description coverage is 100%, so all ten parameters are already documented in the schema, including the non-obvious pagination/redaction semantics on max_results and include_contact_details. The description merely restates which filters exist and adds no format or behavioral detail beyond the schema, so the baseline 3 applies.

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

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

States a specific verb (list) and resource (records, clarified as onboarding requests), and describes the shape of each returned record (status, client name/ID, steps, dates). 'Across the team' gives partial differentiation from the sibling list_client_records, which is client-scoped, but the distinction is never made explicit.

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

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

The filter and sort dimensions are enumerated, which implies when the tool is useful, but there is no explicit when-to-use vs alternatives guidance — nothing tells the agent to prefer list_client_records for a single client or get_record for a single record, despite both being siblings.

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 cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower; the description still adds real semantic value by explaining what a record template actually contains (preset steps, notification, message, reminders, assignees). It stops short of describing pagination behavior, which the schema covers instead.

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

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

A single front-loaded sentence that names the resource first and then triages the kinds with endpoints. The nested parenthetical for record templates is dense but each clause carries information, so no trimming is obvious.

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

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

For a read-only listing tool with full schema coverage and no output schema, the description supplies the semantic context an agent needs to pick the right 'kind'. Nothing critical is missing, though it never says what the returned template objects look like or how they relate to create_record beyond the record case.

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; every parameter is already documented in the schema, including paging and max_results limits. The description only marginally enriches meaning by explaining that 'enabled' yields only enabled or only disabled lists, which the schema also states.

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 verb+resource ('Templates on the team') and enumerates the three template kinds with their backing endpoints (GET /templates/records, /emails, /documents). An agent can immediately tell this apart from the sibling list_records/list_clients/list_webhooks 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?

Usage is implied by the enumeration of kinds and the enabled/disabled scoping option, but there is no explicit guidance on when to choose this tool over list_records or get_record, nor any stated prerequisites. Adequate but leaves the agent to infer route selection.

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

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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds meaningful context beyond them: the signing secret is never returned, and the delivery URL is truncated to origin and path. That is real behavioral disclosure about redaction and response shape, though nothing is said about pagination or rate limits.

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 with no filler; the returned-field summary is front-loaded and the redaction caveat follows immediately. Every clause carries information.

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

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

For a read-only list endpoint with full annotation coverage and a fully documented schema, the description covers what the tool returns and the key security caveat. Pagination is handled in the schema, so little is missing; only the lack of guidance on filtering behavior keeps it from 5.

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 page, enabled and max_results are already fully documented by the schema. The description adds no parameter-level meaning, so the 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?

Specific verb ('List') plus resource ('webhook subscriptions on the team'), and it enumerates the returned fields (delivery URL, subscribed events, enabled flag, dates). It does not explicitly distinguish itself from the many sibling list_* tools, so it stops short of a 5.

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

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

There is no when-to-use guidance, no prerequisites, and no pointer to an alternative or companion tool (e.g. a get_webhook for a single subscription). The only operational note, 'Uses GET /webhooks', is an implementation detail rather than usage direction.

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