Server Quality Checklist

Tool Scores

• citable_backlinksA
  4.1/5.0
  Behavior4/5

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

  Beyond the readOnlyHint annotation, the description discloses that the tool is paid ($0.10 USDC per call) and not charged on failure, which are important operational behaviors. It also sets expectation that the full link profile comes in one call. No contradiction with annotations exists.

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

  Conciseness5/5

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

  The description is short and front-loaded, with pricing first, the core payload second, use-case context third, and failure-pricing reassurance last. Each sentence adds distinct value with no filler.

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

  Completeness5/5

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

  For a read-only tool with two well-documented parameters and no output schema, the description covers what is needed: cost, failure behavior, input expectation (domain), and a clear summary of returned fields. An agent can invoke it correctly without additional context.

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

  Parameters3/5

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

  Schema description coverage is 100%, so both parameters (domain and limit) are already documented in the schema. The description adds little parameter-level meaning beyond confirming that the returned referring domains correspond to the limit parameter.

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

  Purpose4/5

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

  The description clearly identifies the resource: a link/backlink profile with total backlinks, referring domains, domain rank, broken links, nofollow share, and top referring domains. It is specific about what the tool returns, though it does not explicitly differentiate itself from sibling tools like citable_domain_overview or citable_citability_report.

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

  Usage Guidelines4/5

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

  It frames the tool as 'The link-prospecting starting point,' giving an agent clear situational context for when to call it. It does not name alternatives or state when not to use it, but the use-case context is reasonably clear.

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

• citable_citability_reportA
  4.1/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint and openWorldHint, so the lower burden is appropriate. The description adds valuable behavioral context beyond annotations: the exact cost, 'not charged on failure,' and the requirement that the prompt must be user-supplied and never invented. It does not describe output format, but for a read-only report tool this is a minor gap.

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

  Conciseness4/5

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

  The description is compact and every sentence contributes meaningful detail. The price is front-loaded before the core function, which is a slight structural awkwardness, but the overall length is appropriate and each clause earns its place.

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

  Completeness4/5

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

  Given the sibling tools that cover individual components, the description does enough to establish what the bundle includes and why it is priced differently. It could be more explicit about when to choose this over the individual tools, and it omits output format details, but no output schema exists to fill that gap. Overall it provides solid operational context for an agent to select and invoke this tool correctly.

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

  Parameters3/5

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

  Schema description coverage is 100%, so the baseline is 3. The description reinforces the purpose of the domain and prompt parameters but does not add meaning beyond what the schema already provides. The optional limit parameter is fully documented in the schema.

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

  Purpose5/5

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

  The description clearly identifies this as 'full citability report (bundle)' and enumerates the three bundled components: on-page audit, AI visibility, and top AI-cited pages. It also states the three business questions it answers, making the tool's purpose obvious and distinct from sibling tools.

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

  Usage Guidelines4/5

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

  The description strongly implies when to use this tool: when you want all three audit components in one call, with a cost comparison to buying them separately. It does not explicitly name sibling tools or state when NOT to use this tool, but the bundling language and pricing contrast provide clear contextual guidance.

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

• citable_cited_promptsA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and openWorldHint=true, but the description adds substantial behavioral context: it discloses the $0.25 USDC charge per call, notes 'Not charged on failure,' explains collapse of repeated observations with an `observations` count, and clarifies that outputs are observed rather than generated. This goes well beyond the annotations and provides useful operational detail.

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

  Conciseness4/5

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

  The description is compact yet information-dense, starting with the pricing note, then the core function, usage guidance, aggregation behavior, competitor use, and failure policy. Each sentence earns its place, and the structure front-loads the most critical details (pricing and purpose) before elaborating on specifics. Slightly longer than necessary but without fluff.

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

  Completeness5/5

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

  With no output schema, the description compensates well by specifying the return fields: question, answer snippet, AI search volume, and exact URL cited. It also covers payment, failure handling, aggregation, and competitor use cases, making it a complete guide for an agent to call the tool correctly. Nothing essential is missing for a read-only lookup tool.

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

  Parameters3/5

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

  The input schema already describes all three parameters with full coverage (100%). The description adds context about using the `domain` parameter to 'point at a competitor's domain,' which slightly enriches meaning, but it doesn't add significant depth to `limit` or `platform` beyond the schema. Since coverage is high, the baseline of 3 is appropriate.

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

  Purpose5/5

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

  The description clearly identifies the tool's purpose: retrieving real questions that AI answer engines cite a domain for, with specific data elements (question, answer snippet, AI search volume, exact URL cited). It distinguishes from siblings by emphasizing 'observed prompts, never generated ones' and suggests pointing at competitor domains to get prompts they win, which sets it apart from suggestion-based tools like citable_keyword_suggest.

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

  Usage Guidelines4/5

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

  The description provides explicit usage guidance: 'use this to discover what to track instead of inventing them' and 'Point it at a competitor's domain to get the prompts they win and you do not.' This clarifies the intended scenario and differentiates from generated-prompt tools, though it does not explicitly name siblings 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.

• citable_rank_checkA
  4.2/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint/openWorldHint, so the bar is lower, yet the description adds rich extras: the $0.012 USDC per-call cost, 'not charged if the feed is unavailable' failure behavior, and the 1-based position null-if-outside-window edge case. This meaningfully extends beyond the annotations.

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

  Conciseness5/5

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

  Three dense sentences with zero filler. The most operationally critical fact (it is paid) is front-loaded, followed by the core function and return shape, then the no-charge condition. Every sentence earns its place.

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

  Completeness4/5

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

  With no output schema, the description properly carries the return-value burden: it states the position semantics, the URL/title, and the top-10 list. It could add the structure of the top-10 items or error behavior when the domain is absent entirely, but for a moderate-complexity tool this is nearly complete.

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

  Parameters3/5

  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 all 5 parameters. The description adds only a light tie-in ('checked window' ↔ num), but per baseline rules a high-coverage schema carries the burden. No param detail beyond the schema is needed or provided.

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

  Purpose5/5

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

  States a specific verb-resource pair: 'Google organic position of a domain for a keyword via a licensed SERP feed'. The description distinguishes it from siblings like citable_serp (which presumably returns raw SERP) and citable_keyword_metrics (keyword-level data) by making clear it resolves a single domain's position for a single keyword.

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

  Usage Guidelines3/5

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

  The use case is implied — check where a domain ranks for a keyword — and the pricing note adds a practical caution. However, with 18 siblings present, the description never names alternatives or states when-not-to-use (e.g., no routing away from citable_serp or citable_domain_keywords).

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

• citable_top_cited_pagesA
  4.2/5.0
  Behavior4/5

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

  Beyond the readOnlyHint/openWorldHint annotations, the description discloses the $0.22 per-call cost, the no-charge condition when the index is unavailable, and the underlying aggregated AI-answer data source. It does not fully spell out the return shape, but it enumerates the main returned metrics.

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

  Conciseness5/5

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

  The description is compact and every sentence earns its place: pricing, core query, returned metrics, and billing exception. It is front-loaded with the most decision-relevant information and contains no filler.

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

  Completeness4/5

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

  For a read-only reporting tool with simple parameters and no output schema, this description provides enough detail to infer what the call returns. It could mention sort order or the limit default explicitly, but those are recoverable from the schema and the phrase 'top AI-cited pages.'

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

  Parameters3/5

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

  Schema description coverage is 100%, so the schema already documents both domain and limit. The description adds no parameter-specific semantics, so the baseline score of 3 applies.

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

  Purpose5/5

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

  The description names the exact resource—AI-cited pages of a domain—and lists the specific metrics returned: per-page mentions, AI search volume, per-engine and per-language splits, and domain totals. This clearly distinguishes it from sibling tools like citable_serp or citable_ai_visibility without needing to name them.

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

  Usage Guidelines4/5

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

  It gives a clear intended use: identify what already works on a site to inform content strategy ('write more of that'). It does not explicitly contrast with alternatives or give when-not-to-use guidance, but the context is strong enough for an agent to route correctly.

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

• citable_ai_mentions_trendA
  4.3/5.0
  Behavior5/5

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

  Beyond the readOnlyHint and openWorldHint annotations, the description discloses pricing, no charge on failure, statelessness, the index start date, and the one-call-returns-series behavior. This is valuable operational context that annotations alone do not provide.

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

  Conciseness5/5

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

  The description is concise and front-loaded with the most decision-relevant facts: cost, statelessness, what is returned, and the data boundary. Each sentence earns its place with no filler.

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

  Completeness5/5

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

  There is no output schema, but the description adequately explains the return series, the domain scope, the trend calculations, and the call behavior. Cost, failure handling, and index bounds are also covered, making the invocation contract understandable.

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

  Parameters3/5

  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 all parameters. The description adds some contextual meaning like the index start date, but it does not meaningfully enrich individual parameter semantics beyond what the schema provides.

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

  Purpose4/5

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

  The description clearly states the deliverable: monthly AI mentions and AI search volume for a domain, with month-over-month deltas and a direction summary. It distinguishes itself from tracking-style tools by emphasizing stateless, one-call retrieval, but it does not explicitly name sibling alternatives such as citable_ai_visibility or citable_ai_share_of_voice.

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

  Usage Guidelines4/5

  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 is appropriate: a stateless prompt-trend lookup with no tracker creation and no polling. It does not list explicit exclusions or alternatives, so it stops short of a 5.

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

• citable_keyword_researchA
  4.4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint and openWorldHint. Description adds meaningful behavioral context: cost per call, non-charge on failure, merged source logic, and that both-sources is the strongest signal. Does not cover pagination behavior, but reads safe due to annotations.

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

  Conciseness5/5

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

  Five sentences, each carrying essential information: cost, core function, output content, source-strength semantics, and alternative routing. Front-loaded with the pricing and failure policy that matter for invocation decisions.

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

  Completeness4/5

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

  With no output schema, the description explains the return semantics well (merged rows, metrics, source indicator). It also addresses cost, failure, and sibling differentiation. Lacks an explicit note on default page size or output shape, but enough for a competent agent.

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

  Parameters3/5

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

  Schema description coverage is 100%, so baseline 3 applies. Description reinforces 'seed' as the central input and hints that seed is the keyword topic, but adds no new parameter detail beyond schema.

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

  Purpose5/5

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

  Description states a specific verb/resource: one seed returns keywords and questions with volume, CPC, difficulty, intent, merged from autocomplete and paid index. It distinguishes from sibling citable_keyword_ideas and citable_keyword_metrics by explicitly comparing cost and purpose.

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

  Usage Guidelines5/5

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

  Gives explicit when-to-use guidance: use this combined call instead of citable_keyword_ideas plus citable_keyword_metrics; reach for those only when controlling exactly what you pay for. This directly routes an agent to the right choice among siblings.

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

• citable_ai_share_of_voiceA
  4.5/5.0
  Behavior4/5

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

  Beyond the readOnlyHint/openWorldHint annotations, the description discloses meaningful behaviors: per-call pricing regardless of set size, no charge on failure, and the important semantic that share is of the compared set only. This adds practical context an agent needs for decision-making.

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

  Conciseness5/5

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

  Three tightly packed sentences convey pricing, core function, output granularity, and key qualification, all without redundancy. The most decision-relevant facts are front-loaded, and every clause earns its place.

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

  Completeness5/5

  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 return-value burden and does so well: mentions, AI search volume, share, and per-engine/per-language splits. It also covers input constraints, optional platform behavior, and pricing/failure terms, making it sufficient for safe invocation.

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

  Parameters4/5

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

  Schema already covers both parameters well, but the description adds value by tying 'domains' to the 2–10 count and competitive-set comparison, and by noting 'per-engine splits', which clarifies the output effect of the optional platform parameter. It also clarifies that share interpretation depends on the set passed.

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

  Purpose5/5

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

  Description uses a specific verb ('Compare') and resource ('AI-answer index'), and clearly enumerates outputs: mentions, AI search volume, and share of the compared set. It further differentiates itself from siblings by clarifying the share is relative to the requested set, not the whole index.

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

  Usage Guidelines4/5

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

  The description gives clear context for when to use the tool: to compare 2–10 domains in a competitive set. It does not explicitly name alternatives or exclusion criteria, but the 'compare' framing and share-of-set clarification make the intended usage unambiguous.

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

• citable_ai_visibilityA
  4.5/5.0
  Behavior5/5

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

  Beyond the readOnlyHint and openWorldHint annotations, the description discloses the paid nature with exact pricing, the output shape (mentioned, position, cited-domain list), per-engine execution, run-to-run variability, and the no-charge condition. This gives the agent an unusually complete picture of the tool's behavior.

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

  Conciseness5/5

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

  The description is compact but information-dense, front-loading cost and then moving progressively through behavior, output, and repeat-call guidance. Every sentence contributes necessary operational detail with no filler.

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

  Completeness5/5

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

  Even without an output schema, the description defines the return fields well enough for an agent to anticipate results. It covers cost, engine scope, citation mechanics, variability, and a charging edge case, making the tool callable with minimal ambiguity.

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

  Parameters3/5

  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 prompt, domain, and engines. The main description adds cross-cutting context about engines and pricing but does not materially extend the parameter-level semantics beyond what the schema provides. A baseline 3 is appropriate.

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

  Purpose5/5

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

  The description names a specific verb ('asks the AI answer engines... and reports which ones cite the domain'), a concrete resource (AI engines, domain), and clarifies through context that this is an AI visibility check. It clearly differentiates from sibling tools by focusing on live engine citations rather than reports or keyword data.

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

  Usage Guidelines4/5

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

  The description gives a clear context for when to use the tool: checking whether AI engines cite a domain. It also adds practical guidance on calling 2–3 times because answers vary between runs. It does not explicitly contrast with alternatives like citable_citability_report or citable_ai_share_of_voice, so it stops short of a 5.

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

• citable_connectA
  4.5/5.0
  Behavior5/5

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

  Annotations (readOnlyHint=false, openWorldHint=true) already signal mutation and real-world effects, and the description adds substantial context beyond that: the 15-minute link expiry, the significant disk side effect ('installs Para's SDK under ~/.config/citable/para (about 200 MB, once)'), and the state transition semantics of reset (disconnects and returns to keypair) versus status (only reports, no new connection). This is exactly the behavioral context an agent needs before invoking a tool with world effects.

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

  Conciseness5/5

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

  Five dense sentences, each carrying distinct information: audience/pricing, the connection flow, the timeout and follow-up sibling, the flag semantics, and the install side effect. The most decision-relevant facts (free, non-crypto audience, returns a link) are front-loaded. No filler or repetition of schema content.

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

  Completeness5/5

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

  With no output schema, the description correctly explains the return value ('Returns a link to open in a browser'). For a complex tool involving browser interaction, a persistent 200 MB install, a 15-minute expiration, and two mode flags, the description covers the full lifecycle: initiation, confirmation via citable_prices, status reporting, and reset. Nothing an agent needs to call it correctly is missing.

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

  Parameters3/5

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

  Schema coverage is 100% — both boolean parameters already have clear descriptions in the schema ('Forget the sign-in session and pay from the keypair again', 'Only report the current state; do not start a new connection'). The description lightly restates this ({status:true} only reports; {reset:true} disconnects) within the flow narrative, adding marginal value, so the baseline 3 is appropriate.

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

  Purpose5/5

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

  The description states a specific verb and resource — 'connect a sign-in wallet' — and fully explains the mechanism (returns a browser link, sign in with Google/email, add USDC, click Connect). It clearly differentiates from all sibling tools, which are keyword/SEO research tools; citable_connect is uniquely about wallet connection and payment. The flow is concrete enough that an agent knows exactly what this tool accomplishes.

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

  Usage Guidelines4/5

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

  The description gives an explicit alternative: 'when the user says it is done, call citable_prices to confirm (walletMode becomes sign-in)', telling the agent exactly when to switch to a named sibling. It also frames the audience condition ('For people who do not use crypto') and explains the status/reset flags as distinct modes. The when-not case (default keypair path) is only implied via 'returns to the keypair', not explicitly stated, which keeps this short of a 5.

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

• citable_domain_keywordsA
  4.5/5.0
  Behavior5/5

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

  With readOnlyHint and openWorldHint annotations already covering safety, the description adds valuable behavioral context: the per-call cost, the fact that it is not charged on failure, the exact output content, and ordering. This goes beyond what annotations or schema provide.

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

  Conciseness5/5

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

  The description is compact and front-loaded: cost comes first, then the core function and output details, then the competitor use case, then the no-charge behavior. Every sentence earns its place and there is no filler.

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

  Completeness5/5

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

  Even without an output schema, the description enumerates the returned data (volume, CPC, position, movement, URL, total count), sort order, pricing, and intended use. For a read-only lookup tool with fully documented parameters, nothing essential is missing.

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

  Parameters3/5

  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 schema already documents domain, lang, limit, and country with defaults and limits; the description does not add parameter-specific meaning beyond what the schema contains.

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

  Purpose5/5

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

  The description states a specific verb-resource combination: the keywords a domain actually ranks for, with explicit fields (volume, CPC, position, movement, ranking URL) and sort order (highest volume first). It differentiates from sibling tools like keyword_suggest or keyword_research by emphasizing 'actually ranks for' rather than suggestions or metrics.

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

  Usage Guidelines4/5

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

  The description gives a clear use case: 'Point it at a competitor for their playbook,' and the phrasing 'actually ranks for' implies this is for observed rankings rather than keyword ideas. It does not explicitly name alternatives or state when not to use it, but the context is clear enough for an agent to route correctly.

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

• citable_domain_overviewA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint and openWorldHint, so the description does not need to restate that this is a safe, live-data read. It adds valuable context beyond annotations: the paid-per-call pricing, the no-charge-on-failure behavior, and the specific ranking-index data source. This is meaningful behavioral disclosure.

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

  Conciseness5/5

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

  The description is four tight sentences: cost, output scope, usage routing, and billing failure behavior. Every sentence adds distinct information and there is no filler or repetition of schema/annotation content.

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

  Completeness5/5

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

  For a 3-parameter tool with no output schema, the description is complete enough: it states what the call returns, when to call it first, how to follow up with a sibling tool, and the cost implications. The input schema covers parameter details, so an agent has everything needed to select and correctly invoke this tool.

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

  Parameters3/5

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

  Schema description coverage is 100%, with clear schema descriptions for domain ('Hostname to profile'), lang, and country. The tool description itself only reinforces that the target is 'one domain' and does not add detail about lang/country defaults or formats, so it matches the baseline for fully-covered schemas without extra value.

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

  Purpose5/5

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

  The description clearly states the tool returns one domain's organic footprint from a ranking index, listing concrete outputs: keywords ranked, top-3/top-10 counts, estimated traffic, ad value, and paid-search side. It names citable_domain_keywords as a distinct follow-up tool, so an agent can tell this overview apart from siblings.

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

  Usage Guidelines5/5

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

  It explicitly says this is 'the first call for any domain question' and then directs agents to citable_domain_keywords for detailed ranking data. It also gives practical cost guidance ($0.03 USDC per call, not charged on failure), which helps an agent decide when invoking this tool is appropriate.

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

• citable_keyword_suggestA
  4.5/5.0
  Behavior5/5

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

  Beyond the readOnlyHint and openWorldHint annotations, the description discloses the paid cost per call, deduplication and ranking behavior, the sources searched, and the exact return shape including suggestions[], questions[], prominence scores, and source attribution. This is substantial behavioral context not already present in the annotations.

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

  Conciseness5/5

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

  The description is one dense, front-loaded sentence that begins with the critical paid-call warning and then efficiently conveys behavior, sources, and output structure. There is no filler or redundant restatement of the title or schema.

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

  Completeness5/5

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

  Even though there is no output schema, the description explains the return format, scoring, sources, and seed-containment check. Combined with complete parameter documentation and annotations signaling read-only and open-world behavior, the agent has enough context to invoke the tool correctly.

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

  Parameters3/5

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

  The input schema already documents 100% of parameters with descriptions, defaults, and constraints, so the baseline is 3. The tool description adds context about output structure but does not significantly enhance parameter-level meaning beyond what the schema already provides.

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

  Purpose5/5

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

  The description clearly states a specific action and resource: expands a seed keyword into autocomplete suggestions, related queries, and questions. It distinguishes itself from sibling keyword tools by emphasizing the seed-based, cross-engine nature, and the schema explicitly contrasts it with citable_domain_keywords for domain-level keyword queries.

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

  Usage Guidelines4/5

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

  The description makes clear this is for expanding a seed keyword rather than analyzing a domain, and the seed parameter explicitly says 'Not a domain' and routes domain-keyword use to citable_domain_keywords. However, it does not compare itself against close siblings like citable_keyword_ideas or citable_keyword_research, so the guidance is good but not exhaustive.

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

• citable_serpA
  4.5/5.0
  Behavior4/5

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

  The annotations already declare readOnlyHint=true and openWorldHint=true, so the description's job is lighter. It adds meaningful context beyond annotations: the per-call price, that failures are not charged, and that auxiliary sections appear only when present. No contradiction or hidden write behavior is indicated.

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

  Conciseness5/5

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

  Four short sentences each carry distinct information: cost, return shape/contents, differentiation from rank-check, and failure billing. The key facts are front-loaded, with no filler.

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

  Completeness5/5

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

  With no output schema, the description compensates by describing what the response contains (organic snippets, PAA, related searches) and how to distinguish the tool from siblings. Together with the fully documented input schema and annotations, an agent has enough to invoke it correctly.

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

  Parameters3/5

  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 all four parameters including defaults, bounds, and the keyword semantics. The description mostly restates that the keyword is the query and adds nothing new about parameter syntax or formatting.

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

  Purpose5/5

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

  The description states the tool returns the raw Google results page for a keyword, enumerating the content (organic results with snippets, People-Also-Ask, related searches) and explicitly contrasts it with rank-check ('answers where am I; this answers what the page looks like'), which clearly separates it from siblings.

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

  Usage Guidelines5/5

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

  The description names the key alternative, citable_rank_check, and states the decision rule: use rank-check for position answers and this for what the page looks like. It also surfaces cost and no-charge-on-failure, which helps an agent decide whether this paid tool is appropriate.

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

• citable_keyword_metricsA
  4.7/5.0
  Behavior5/5

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

  Beyond readOnlyHint/openWorldHint, the description discloses per-call billing, batch-level pricing, answers in request order, null metrics for unknown keywords, licensed clickstream-derived data provenance, and a no-charge fallback if the metrics feed is unavailable. These are behavioral facts an agent could not infer from the schema or annotations, and none contradict the read-only annotation.

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

  Conciseness5/5

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

  Four dense sentences with zero wasted words: cost, deliverable, response behavior, sibling routing, and billing fallback. The most operationally salient fact (price) is front-loaded before the feature list, and each clause adds distinct information.

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

  Completeness5/5

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

  For a 3-parameter read-only tool with no output schema, the description covers the deliverable, input bounds, cost, response ordering, null failure mode, data provenance, and the sibling workflow. Nothing an agent needs to invoke it correctly or interpret its results is missing.

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

  Parameters3/5

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

  Schema description coverage is 100%, so the baseline applies: the schema already documents the comma-list format and 1–20 keyword constraint. The description reinforces the batch size and adds the null-response behavior for unknown keywords, but it does not add new parameter-level semantics beyond what the schema already states.

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

  Purpose5/5

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

  The description names a specific deliverable — 'Search volume, CPC, competition, keyword difficulty and search intent for 1–20 keywords' — with a precise resource (keyword metrics) and a bounded input size. The pairing line with citable_keyword_suggest explicitly differentiates this pricing tool from its closest sibling, so an agent can tell them apart without opening the schema.

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

  Usage Guidelines5/5

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

  'Pair with citable_keyword_suggest: expand a seed there, price the shortlist here' is an explicit workflow rule naming the alternative and the condition that selects each tool. It also surfaces the cost model ('$0.03 USDC per call') as a practical usage consideration, and the 'not charged if the metrics feed is unavailable' line clarifies the billing edge case.

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

• citable_onpage_auditA
  4.7/5.0
  Behavior5/5

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

  The description discloses the paid nature ($0.01 USDC per call) and the no-charge condition if the page cannot be fetched — important behavioral information not present in annotations. It also includes a comprehensive list of returned data elements, giving the agent a full picture of what to expect. The readOnlyHint is consistent with 'fetches' and openWorldHint with external URL access, so no contradiction.

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

  Conciseness5/5

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

  The description is two sentences with zero filler. It front-loads the cost and core function, then lists outputs and conditions efficiently. Every word adds value, making it highly scannable for an agent.

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

  Completeness5/5

  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 fully enumerate return values — it does, listing all key audit components and the scoring system. It also covers cost, no-charge behavior, and alternative tools, leaving no critical gaps for an agent to call it correctly.

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

  Parameters3/5

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

  The input schema provides a complete description of the 'url' parameter, including the requirement for an absolute http(s) URL and the note about domain-level tools. The tool description does not add any additional parameter semantics beyond what the schema already covers, so the baseline of 3 applies.

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

  Purpose5/5

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

  The description is explicit: 'Fetches one URL and returns a scored on-page audit' and enumerates the exact outputs (title, meta description, canonical, etc.). It also distinguishes itself from siblings by stating that domain-level views should use citable_domain_overview or citable_citability_report, making its scope unambiguous.

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

  Usage Guidelines5/5

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

  The description clearly tells the agent when to use this tool (single URL audit) and when not to, explicitly naming alternative tools for domain-level queries. This is direct guidance that prevents misuse and corrects potential confusion.

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

• citable_pricesA
  4.7/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint=true, and the description adds meaningful behavioral context beyond that: the tool is free, reports wallet funding status, and can return empty results that require a setup fallback. This is useful and consistent with the annotations.

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

  Conciseness5/5

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

  Three dense sentences deliver essential information with no filler: what the tool returns, the fallback when empty, and the call-first instruction. Key behavioral guidance is front-loaded.

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

  Completeness5/5

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

  With no input schema parameters and no output schema, the description carries the full burden of explaining the return fields, pricing context, wallet funding, and next-step behavior. It covers all of these clearly, including the empty-case handling and the directive to call this first.

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

  Parameters4/5

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

  The tool has zero parameters and the schema confirms this, so parameter-level description is unnecessary. The description appropriately focuses on what the tool returns rather than input semantics, matching the baseline for a parameterless tool.

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

  Purpose5/5

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

  The description clearly states the tool lists Citable's SEO endpoints with current per-call USDC prices and the wallet that pays. This is specific and distinguishes the tool from sibling data-gathering tools because it is a meta-resource for endpoint access and pricing.

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

  Usage Guidelines5/5

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

  The description explicitly instructs the agent to call this tool first, establishing clear sequencing relative to the many sibling Citable tools. It also specifies what to do when the result is empty: surface the two funding methods provided by `setup` to the user.

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

• citable_domain_historyA
  4.8/5.0
  Behavior5/5

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

  Beyond the readOnlyHint and openWorldHint annotations, the description adds cost ($0.03 per call), partial-month caveat, statelessness ('nothing is stored'), and 'not charged on failure' — all useful operational details that help an agent set expectations. These are not redundant with annotations.

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

  Conciseness5/5

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

  The description is front-loaded with cost and core purpose, then lists metrics and unique attributes, ending with a routing note. Every sentence earns its place; it is dense but not bloated, and the structure leads with the most important decision-relevant information.

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

  Completeness4/5

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

  For a read-only tool with no output schema, the description covers what data is returned (provided metrics), the time granularity, the caveat about partial month, and pricing. It could mention pagination or response structure, but given the simplicity and openWorldHint, it is sufficiently complete for an agent to invoke correctly.

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

  Parameters4/5

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

  Schema coverage is 100% and each parameter has a description. The description adds value by tying the 'months' parameter to 'the current month may be partial,' clarifying how the range affects data interpretation — meaning beyond what the schema states. This is above the baseline 3.

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

  Purpose5/5

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

  The description states a clear purpose: it shows a domain's organic footprint changes month by month, listing concrete metrics (keywords ranked, top-10 count, traffic, value, keyword movements) and explicitly contrasts with citable_rank_check for single-keyword today. This distinguishes it from sibling tools and gives a specific verb+resource.

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

  Usage Guidelines5/5

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

  It explicitly states when to use (tracking monthly history of rankings) and when not ('for one keyword's position today use citable_rank_check'), naming the alternative and the condition. This provides clear guidance for tool selection.

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

• citable_keyword_ideasA
  4.9/5.0
  Behavior5/5

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

  Beyond the readOnlyHint and openWorldHint annotations, the description discloses a $0.05 USDC per-call cost, states that failures are not charged, and specifies ordering by volume. This is valuable operational context that the annotations do not provide, and it sets correct expectations for an agent.

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

  Conciseness5/5

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

  Four short sentences, each carrying distinct value: cost, output behavior, differentiation from siblings, and failure policy. The most important information is front-loaded, and there is no filler or repetition of schema details.

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

  Completeness5/5

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

  Despite having no output schema, the description specifies exactly what the response contains: up to 100 keywords with search volume, CPC, competition, difficulty, intent, ordered by volume. Combined with full parameter schema coverage, sibling differentiation, and cost transparency, nothing essential is missing for an agent to invoke this tool correctly.

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

  Parameters4/5

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

  Schema coverage is 100%, so parameters like seed, lang, limit, and country are already documented. The description adds meaningful interpretation: results are full-text matched so they stay on topic, and the seed is implied to be a topic rather than a domain. This goes beyond a baseline schema-only understanding.

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

  Purpose5/5

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

  The description opens with a precise, actionable statement: one seed returns up to 100 containing keywords with volume, CPC, competition, difficulty, and intent, ordered by volume. It clearly separates this tool from citable_keyword_suggest and citable_keyword_metrics, so an agent can identify its distinct role without opening schemas.

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

  Usage Guidelines5/5

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

  The description explicitly tells the agent when to use this tool versus sibling tools: use citable_keyword_suggest for exact phrasings people type, and citable_keyword_metrics when a shortlist already exists. It also clarifies the matching behavior (full-text, on-topic), which helps the agent decide if this tool fits the task.

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