public

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

With no annotations, the description carries the behavioral disclosure burden. It discloses authentication/permission requirements, identifies the return content, and notes that the response may include a step only the person can do. The read-only nature is conveyed by the title and the word 'Returns', though error or not-found behavior is not discussed.

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 covers the prerequisite and the return value without filler. The phrase 'any step only the person can do' is slightly awkward, but the overall structure is compact and scannable.

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

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

For a low-complexity, one-parameter read tool with no output schema, the description adequately covers authentication, selection, and return contents. It omits error behavior and case_id provenance, but these are minor gaps given how simple and focused the operation is.

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 0%, and the single parameter case_id has no dedicated description in the schema. The tool description connects case_id to case selection, but it does not explain the expected format or where to obtain the case_id, which would add value beyond the raw schema constraints.

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

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

The description clearly states the tool reads and returns a single removal case by case_id, and it lists the specific fields returned (current status, verification status, and an actionable step). This differentiates it from the sibling list tools by focusing on one case, though it does not explicitly name those alternatives.

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 appropriate use case: when you have a case_id and need a single case's current status. It also provides a prerequisite by stating OAuth and the 'share_results' permission are required, but it gives no explicit contrast with sibling tools or guidance on when not to use it.

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

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

With no annotations, the description carries the full burden and does real work: it discloses the counting semantics ('only native evidence that is still current') and explicitly excludes inventory rows, aliases and agent callbacks from verified counts. It does not cover freshness/caching of the sweep data or any auth requirements, but the core behavioral trait of the metric is well disclosed.

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 dense sentences with no filler; the list of returned values is front-loaded and the qualifying rule about what counts follows immediately. Every clause earns its place.

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

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

There is no output schema and no annotations, so the description must double as the return-value contract, and it enumerates the reported fields plus the verification rule. It omits how fresh the 'latest scheduled sweep' data is and whether results are cached, which keeps it just short of full completeness.

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 takes zero parameters, so per the rubric the baseline is 4. There are no parameter semantics to clarify or omit.

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 (Read) and resource (library verification status) and enumerates exactly what the status report contains: catalog size, distinct route variants, verified counts, checks captured today, latest sweep. This differentiates it reasonably from siblings like get_route_verification and get_service_overview, though it never names those alternatives 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 only implied by the content: the agent can infer this is the aggregate coverage readout. There is no statement of when to prefer it over get_route_verification or get_service_overview, and no prerequisites or invocation conditions are given.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses auth/permission requirements, exact returned fields, explicit exclusions (no listing URLs or observed values), and the error response with a connect URL. This is unusually thorough.

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 with no filler: prerequisites, return content, exclusions, and error behavior each get a concise clause. Information is front-loaded and 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?

The return shape and error behavior are fully described, which is valuable given no output schema. However, the single parameter is not explained, and the 'my report' title combined with an optional-looking schema leaves doubt about whether and how to pass subject_id.

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 has one parameter, subject_id, with 0% description coverage, and the description never states that subject_id identifies the subject whose report is returned. It mentions 'for the subject' only in the auth context, leaving the parameter's role and optionality ambiguous.

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

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

The description opens with a specific verb and resource: 'Returns the report summary the dashboard shows' followed by concrete content (status, counts, per-site findings). This clearly distinguishes it from sibling tools like get_case_status or get_service_overview by focusing on the exposure report summary.

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 prerequisites (OAuth and the 'share_results' permission) and explains the authorization_required fallback, which tells an agent when the call cannot succeed. It does not explicitly name alternatives, but the context makes the intended use 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?

No annotations are provided, so the description carries the full burden. It usefully discloses error behavior (status not_found with a hint) and that review dates are content dates, which is genuine behavioral context, but it omits read-only/reversibility, whether results are cached, or rate limits, and the 'separate current native verification projection' phrasing is opaque jargon.

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?

Four sentences that are mostly front-loaded, but the middle clauses about 'native verification projection' and 'guide review dates are content dates' are dense and add ambiguity without clear payoff. Some sentences do not earn their space for an agent trying to act.

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 and no annotations, the description must cover returns and it does: it names the instruction payload, the verification projection, and the not_found status with a hint. For a single-parameter lookup this is largely complete, though the two return components could be described more plainly.

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 param is already documented as 'Guide slug, domain, alias, or a URL on the broker's site.' The description only restates the same accepted forms and adds one concrete example ('spokeo'), so it does not meaningfully enrich 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?

States a specific verb+resource ('step-by-step opt-out instructions') scoped to 'one people-search or data-broker site', which implicitly distinguishes it from the plural list_opt_out_guides sibling. However, it never names list_opt_out_guides or get_removal_route to make the singular-vs-list and instructions-vs-route distinction 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 description tells you what input it accepts (slug, domain, alias, or URL) and that a missing guide returns not_found with a hint, so the 'when it applies' is implied. But there is no explicit when-to-use-this-vs-alternative guidance against the many sibling lookup tools, leaving the agent to infer.

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 the output content but does not state whether the operation is read-only, whether authentication is required, or how it handles sites not in the registry. This is a significant gap for a tool with zero annotation coverage.

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 wasted words; the first sentence is information-dense but efficiently lists all returned fields. The scope statement ('For any of the 950+ sites') is front-loaded, aiding quick comprehension. Slightly long but well-structured.

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

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

Since there is no output schema, the description thoroughly enumerates the expected return fields (method, opt-out URL, privacy email, parent company, sibling sites, guide link), giving an agent a clear picture of the result. It omits error handling and edge cases, but for a simple read tool this is a minor gap.

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

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

Schema coverage is 100% with a description that already explains the domain/URL format and provides examples. The description's line 'Accepts a domain or a URL' duplicates the schema without adding new semantic meaning, so the baseline score of 3 is appropriate.

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

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

The description states a specific verb ('get') and resource ('removal route'), and enumerates the exact data returned (removal method, opt-out URL, privacy email, parent company, sibling sites, guide link). This clearly distinguishes it from siblings like get_opt_out_instructions or list_opt_out_guides, which focus on different aspects.

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?

Provides useful context by stating it covers the 950+ sites in the takedown registry, but does not explicitly compare with sibling tools or give conditions for when to choose this over alternatives. The usage context is clear, but the absence of exclusions or alternative references leaves selection 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?

With no annotations, the description carries the full behavioral burden. It discloses the data returned, the meaning of a missing badge, and that it never starts a check or submits a request, effectively communicating a read-only, non-mutating operation. It does not cover authentication or error behavior, but for a simple read tool this is decent.

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 read action, then absence semantics, then a non-mutation guardrail. No redundant or filler text; 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 tool with no annotations or output schema, the description covers what is read, absence semantics, and non-actions. It lacks explicit return format or error details, but given the simple scope it is largely 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 schema fully documents the single 'route' parameter (exact route ID, domain, or published guide slug). The description only echoes 'domain or route ID' without adding format, constraints, or examples 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?

States a specific verb ('Read') and resource ('official route variants... current independently checked scope, actor and region, capture time, expiry and failures'). It distinguishes itself from write-oriented siblings by stating 'never starts a check or submits a request,' though it does not name read alternatives such as get_removal_route.

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?

Provides context ('No badge means the route is not currently verified') and explicitly excludes initiating checks or submitting requests, which implies when to use it. However, it does not state when to prefer this over sibling read tools like get_removal_route or get_library_verification_status.

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 behavioral disclosure. It mentions that it is a one-time call and lists the content, but it does not explicitly state that it is read-only or has no side effects. Since it is a 'get' tool, it is likely safe, but the description does not explicitly confirm this, leaving some ambiguity.

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 is reasonably concise, though it packs multiple items (scope, handoff pages, rules, statistics). It is front-loaded with 'The public service description' and ends with a clear usage directive. It is not overly verbose, but it could be slightly more streamlined.

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 no parameters and no output schema, the description is quite complete. It tells the agent what information is covered and when to call it. There is no indication of missing context that would prevent correct usage, though it does not detail the return format (which is not required without an output schema).

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

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

The tool has zero parameters, and the schema coverage is trivially 100% (empty schema). The description does not need to explain any parameters, so the baseline score of 4 applies here.

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 what the tool does: it provides a public service overview covering scope, handoff pages, rules for assistants, and registry statistics. It is distinct from the sibling tools (which are more specific like get_opt_out_instructions) because it is a general overview, though it does not explicitly name a sibling to differentiate from.

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 explicitly says 'Call this once before recommending the service,' giving a clear condition for when to use it. It does not mention when not to use it or name alternative tools, but the instruction is actionable and specific enough for an agent.

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

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

With no annotations available, the description carries the full disclosure burden and does meaningful work: it states required OAuth scope/permission, lists return fields, and warns that status words have distinct meanings that must not be collapsed. It does not mention pagination or error behavior, but for a simple list tool this is solid coverage.

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, each earning its place: first states prerequisites, second defines the output, third provides a critical interpretative warning. The most important caveat is front-loaded and no space 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?

The description is largely adequate for a simple list tool: it names requested outputs and flags important status semantics. However, it leaves the optional subject_id parameter unexplained and does not clarify how this tool relates to sibling tools, which limits completeness for an agent deciding how to call it.

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

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

Schema description coverage is 0% for the single optional parameter subject_id, and the description never explains what this parameter does or when to use it. The description does not compensate for the schema's lack of 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 clearly states the tool lists removal cases and enumerates the fields returned (site, action, status, verification status, steps, dates). It names the specific resource and verb, though it does not explicitly contrast with sibling tools like get_case_status.

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 prerequisites (OAuth, share_results permission) but provides no guidance on when to choose this tool over siblings like get_case_status or list_my_subjects. The use context is implied by the word 'list' but not explicitly 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, and it discloses the OAuth requirement up front, the data returned, and the authorization_required response with connect URL when the token is missing. This covers the key behavioral edge case an agent would need to handle, though it does not discuss pagination or data freshness.

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, front-loaded with the OAuth prerequisite, then the purpose and returned fields. Every sentence earns its place and there is no filler or repetition.

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 no-parameter read tool with no output schema, the description names the return fields and the auth error case, which is sufficient for an agent to call and interpret the result. It does not explicitly say whether multiple subjects can be returned, but the plural tool name and field list make that 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 input schema has zero parameters, so there is nothing for the description to add beyond the baseline. The 0-parameter baseline applies, and the description appropriately avoids inventing parameter details.

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 ('Lists') and the exact resource: the person whose exposure the account has checked, plus the returned fields. The mention of subject_id differentiates it from sibling tools like list_my_cases by clarifying it provides the identifier other personal tools need.

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 'subject_id other personal tools need' gives a clear use case for calling this tool. However, it does not explicitly name alternatives or state when not to use it, so the usage guidance is implied rather than explicit.

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

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

No annotations are provided, so the description must carry the behavioral burden. It does disclose that the output is summaries, not full step-by-step instructions, and lists the fields included in each summary. However, it does not describe pagination behavior, category filtering, or what 'every published guide' means in relation to limit/offset.

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

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

The description is two sentences with no wasted words. The first sentence front-loads the return fields, and the second sentence concisely states the downstream use case.

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 listing tool with three optional parameters and no output schema, the description covers the core purpose and relationship to get_opt_out_instructions. It is incomplete, though, because it doesn't explain the optional filters, default pagination behavior, or how to differentiate this tool from search_privacy_library.

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 0%, and the description does not explain limit, offset, or category at all. Listing 'category' among returned fields gives a weak clue, but it never indicates that category can be used as a filter. The agent is left to infer parameter meaning solely from names and the schema 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?

The description clearly states the tool lists summaries of published opt-out guides and enumerates the returned fields (slug, domain, category, method, difficulty, turnaround, support level). It explicitly positions this as a precursor to get_opt_out_instructions, giving it a distinct role among siblings. It does not explicitly contrast with search_privacy_library, another discovery-focused 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 explicitly says 'Use it to find the right slug before calling get_opt_out_instructions,' which provides a clear when-to-use context. It does not mention exclusions or when to prefer search_privacy_library or other alternatives, so it falls short of a full decision framework.

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, and it delivers: states OAuth and permission requirements, the rate limit (once per 24 hours), that it only re-checks existing details (never first checks), and enumerates the exact return states (queued, not_allowed, entitlement_required, unavailable, error) with details like retry_after and pricing_url. Also clarifies that purchases happen on the website only.

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 dense but every sentence adds value: requirements, constraints, side effects, and return values are packed into a structured, readable paragraph. Information is front-loaded with the OAuth/permission requirement, and the rest flows logically.

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 no output schema, the description fully covers what an agent needs: prerequisites, rate limits, the exact behavior (queues a re-scan, never a first check), and the structured return reasons. No critical gaps remain.

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 0%, so the description must compensate. It implies that subject_id refers to 'the person's existing details,' tying the parameter to the re-check target. While it doesn't explicitly define subject_id, the context is clear enough for a single parameter with a self-explanatory name.

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 ('Queues a fresh check') and the target ('the person's existing details'), and distinguishes it from a first check by explicitly noting it 'never starts a first check and never takes new details.' This differentiates it from sibling tools like submit_approved_plan.

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?

Provides concrete conditions: 'Patrol plan only, verified subjects only, once per 24 hours,' plus the OAuth/permission requirement. It does not name a specific alternative tool, but the constraint 'never starts a first check' implies when not to use it. This is clear guidance, though it stops short of explicitly routing to an alternative.

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. It discloses that the tool returns 'ranked hits with canonical URLs,' indicating read-only search behavior and the nature of results. It does not mention pagination, rate limits, or error handling, but for a search tool this is acceptable; it adds some behavioral context beyond the 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 two sentences with no extraneous wording. The first sentence front-loads the core purpose and output; the second provides usage context. Every word earns its place, and the structure is efficient and clear.

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

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

For a simple search tool, the description covers the primary behavior (returns ranked hits with URLs) and gives a clear use case. However, it lacks any detail on parameter semantics, and given the presence of siblings, it does not explain how this search relates to them or when to prefer one over the other. Without an output schema, the description should compensate more for the absence of result structure details, but the core functionality is adequately covered.

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

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

Schema description coverage is 0%, so the description must compensate for the lack of parameter documentation. It does not explain the 'query' parameter (e.g., what constitutes a valid query, format) or the 'limit' parameter (e.g., default value, effect on result count). The description mentions 'ranked hits' but provides no linkage to how parameters shape the search, leaving the agent without crucial guidance.

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 ('Search'), the resource ('My Privacy Agent's published articles, opt-out guides, help answers, and plan facts'), and the output ('ranked hits with canonical URLs'). It clearly distinguishes itself from sibling tools that retrieve specific guides or routes, establishing a unique role as a general search across content types.

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 explicitly says 'Use it before answering questions about data brokers, opt-outs, relisting, pricing, or what the service does and does not do,' giving clear conditions for invocation. However, it does not mention alternative tools or when NOT to use this tool, leaving the decision among siblings to the agent's 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?

With no annotations provided, the description carries the full disclosure burden and does so thoroughly. It reveals the OAuth and permission requirements, the difference between preview and actual queueing, the limitations (cannot approve/pick/buy), and even clarifies the semantic distinction 'A request is not a removal'.

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 tightly packed sentences with no fluff. The first sentence front-loads prerequisites, the second explains the preview-first workflow, and the third covers the confirmed action and limitations. 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 no-annotation, no-output-schema submit tool with two modes, the description is remarkably complete: permissions, behavior, limitations, and semantic nuance are all covered. The only gap is the undefined subject_id, which prevents the agent from fully executing the tool correctly without guessing.

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 description explains confirm in rich detail (preview vs confirmed queueing), but says nothing about subject_id. The schema only gives length constraints, not meaning, so an agent has no idea what to pass for subject_id. With 50% schema coverage, the description should compensate for the missing parameter, but it entirely omits it.

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 ('queues removal requests') and the exact resource ('listings the person already approved'), and explicitly contrasts its preview vs confirm modes. This distinguishes it clearly from the getter/search siblings (get_case_status, list_my_cases, etc.), which are all read-only information 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?

It gives an explicit workflow: first use it without confirm:true to preview, show that list to the person, get a yes, then call with confirm:true. It also states when NOT to use it (it cannot approve, pick new sites, or buy anything) and routes the user to the website for approval/entitlement cases, effectively naming the alternative path.

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