Server Quality Checklist

Tool Scores

• get_article_contentA
  4.2/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful context about downloading/parsing and summarizing, but does not disclose behavior around invalid URLs, paywalls, or fallback outcomes. This is acceptable given the annotations, but not especially rich.

  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?

  Two concise sentences front-load the core action and condition, then immediately give the routing exclusion. Every sentence earns its place and there is no fluff.

  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 single-URL read tool with full schema coverage and an output schema, the description covers use case, scope, and alternatives. It does not discuss edge cases like malformed URLs or unavailable articles, but these are minor gaps for this simple safe-read 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%, so the schema already documents all three parameters well. The description adds a high-level hint about retrieving text/metadata or summarizing, but does not materially improve on the schema's own descriptions. 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 clearly states the tool's specific verb ('Download and parse') and resource ('one specific news article... when you already have an article URL'). It also explicitly scopes this away from discovery, distinguishing it from sibling search/trend tools even without opening their 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?

  It gives an explicit when-to-use condition ('when you already have an article URL') and a clear exclusion with the alternative ('do not use it for discovery - use the news search tools instead'). This is direct and actionable for an agent.

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

• get_news_by_topicA
  4.2/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds useful context about the tool's scope ('predefined topic') and recency ('recent'), but it doesn't discuss result volume, limits, or behavior beyond what annotations and schema imply. This is adequate but not rich.

  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?

  Two sentences with no filler. The core purpose is stated first, followed immediately by usage guidance and the sibling distinction. Every word 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?

  The definition is largely complete because the output schema exists, annotations cover safety, and the description provides clear purpose and routing. However, it doesn't point the agent to get_categories for discovering valid topic values, which would be helpful since the topic field has no enum or list.

  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 is 3. The description adds minor value by giving examples of valid topic values ('BUSINESS, TECHNOLOGY, or SPORTS') and clarifying that the topic must be a predefined category, but it does not elaborate on the other parameters.

  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 ('Find'), a resource ('recent Google News articles'), and a clear scope ('predefined Google News topic category'). It also distinguishes itself from the most similar sibling by naming get_news_by_keyword for free-form queries.

  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 ('for topic category browsing') and when to use the alternative ('use get_news_by_keyword for a free-form query'). This is a direct when-to-use vs. when-not-to-use statement.

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

• get_growthA
  4.3/5.0
  Behavior3/5

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

  Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false), and the description adds limited behavioral context beyond that. The word 'estimate' hints at approximate computation, but the description does not detail rate limits, data freshness, or edge cases. With annotations shouldering the main safety burden, a 3 reflects adequate but not rich 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 two sentences with zero redundancy. The primary purpose is front-loaded, and the alternative tool mention is placed second as a helpful routing cue. Every sentence 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?

  Given the presence of a complete input schema (100% coverage), an output schema, and read-only annotations, the description sufficiently covers the tool's purpose, usage boundary, and relationship to a sibling. Nothing essential for an agent to select and call the tool correctly appears 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 is 3. The description's phrase 'growth windows' loosely aligns with the percent_growth parameter, but it does not add syntax, defaults, or formatting details beyond what the schema already provides. No additional parameter meaning is contributed.

  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 uses a specific verb ('Estimate momentum') plus a clear resource ('one or more known keywords') and scope ('across requested growth windows'). It explicitly distinguishes itself from get_trends by contrasting percentage growth with underlying historical time series, making its purpose 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 provides a direct selection rule: 'Use this when percentage growth is the goal; use get_trends when the user needs the underlying historical time series.' This explicitly identifies when to choose this tool over a named sibling, leaving no inference required.

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

• get_interest_by_regionA
  4.3/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is well covered. The description adds useful scope context ('known keywords', geographic resolution) but does not disclose deeper behavioral traits such as normalized scoring, empty results behavior, or API limitations beyond what the output schema and annotations already imply.

  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 no fluff. The first sentence states the core function and scope; the second provides usage guidance and a direct alternative. The most important routing information 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 a 100% schema-covered parameter list, an output schema, and helpful annotations, the description only needs to clarify selection logic. It does that by identifying the geographic comparison use case and naming get_trends as the time-series alternative. No critical information for invoking the tool 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 description coverage is 100%, so the baseline is 3 even without parameter details in the description. The description adds the 'known keywords' nuance and repeats resolution values already present in the schema, but it does not substantially enrich parameter semantics beyond structured documentation.

  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 specific verb and resource: 'Return geographic Google Trends interest' for one or more known keywords at defined resolutions. It clearly differentiates from the sibling get_trends by framing this tool as geographic/comparison-oriented rather than time-oriented.

  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 gives an explicit when-to-use signal ('compare where demand is strongest') and an explicit alternative ('use get_trends for interest over time instead'). This gives an agent enough routing information without needing to inspect sibling schemas.

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

• get_news_by_keywordA
  4.3/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds useful context about querying Google News and accepting free-form phrases, matching openWorldHint. However, it does not disclose pagination, result ordering, or how 'recent' relates to the period parameter, so behavioral richness beyond annotations is moderate.

  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 no filler: the first states what the tool does, and the second provides sibling routing. Every sentence earns its place, and the most important purpose information 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?

  For a read-only search tool with an output schema, full parameter documentation in the schema, and clear sibling differentiation, the description covers what an agent needs to select and invoke it. Missing details like result format are handled by the output schema, and safety is covered by annotations.

  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 all five parameters are already documented. The phrase 'free-form keyword or phrase' reinforces the keyword parameter's intent but adds little beyond the schema's 'Search term to find articles.' With full schema coverage, 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 opens with a specific verb and resource: 'Find recent Google News articles' for a free-form keyword or phrase. It also distinguishes itself from siblings by naming get_news_by_topic and get_news_by_site as the tools for predefined categories and single publishers.

  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 this tool ('ad-hoc subject searches') and points to concrete alternatives: get_news_by_topic for predefined topic categories and get_news_by_site for a single publisher. This gives an agent clear routing guidance without needing to inspect sibling schemas.

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

• get_news_by_siteA
  4.3/5.0
  Behavior3/5

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

  The annotations cover the key safety profile (readOnlyHint=true, destructiveHint=false), so the description does not need to restate that. It adds useful context about scoping to a publisher domain and recency, but it does not mention pagination, rate limits, or how results are structured beyond what the output schema likely provides. This is adequate but not especially rich.

  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?

  Two sentences with no filler: the first states the core function and scope, the second gives sibling routing. Every sentence earns its place and the key information 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?

  For a read-only news retrieval tool with a detailed input schema and output schema, the description provides sufficient context. It specifies the domain-scoping behavior, the recency framing, and the main alternative, so an agent can decide when to call this tool and what to expect at a high level.

  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 five parameters clearly. The description adds a 'publisher domain' and 'recent' framing that loosely map to the site and period parameters, but it does not provide substantive parameter-level meaning beyond 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 the tool as retrieving recent Google News articles from a single publisher domain, with a specific verb ('Find') and resource ('Google News articles'). It also distinguishes itself from get_news_by_keyword, making the tool's scope immediately understandable.

  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 states when to use this tool ('when the user wants source-specific coverage') and directly names the alternative for cross-publisher subject search ('use get_news_by_keyword'). This gives an agent clear routing guidance with no inference required.

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

• get_related_topicsA
  4.3/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds useful context about returning 'top and rising' topic entities, but does not disclose any additional behavioral traits such as limits, pagination, or data source nuances. This matches the bar for a read-only tool 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?

  Two sentences, no fluff. The primary purpose is front-loaded, and the sibling guidance is compact and directly actionable. Every word 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?

  Given the presence of an output schema, detailed parameter descriptions, and safety annotations, the description is fully sufficient. It clarifies the tool's niche relative to a key sibling and states the core use case without omitting anything an agent needs 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?

  Schema coverage is 100%, so the schema already documents all five parameters thoroughly. The description adds slight semantic value by calling the keyword a 'seed', implying it is the basis for expansion, but does not materially enrich parameter understanding beyond 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 states a specific verb ('Return'), a precise resource ('Google Trends topic entities'), and a clear scope ('related to one seed keyword'). It also differentiates from get_related_queries, making the tool immediately distinguishable from its closest sibling.

  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 tells the agent when to use this tool ('for entity or topic expansion') and when to use an alternative ('use get_related_queries for literal search queries'). This leaves no ambiguity about selection.

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

• get_top_newsA
  4.3/5.0
  Behavior3/5

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

  Annotations already carry the safety profile (readOnlyHint=true, destructiveHint=false), so the description's additional behavioral burden is low. It does add the scoping fact that no seed is required, but it does not mention pagination, default result caps, or potential data freshness limitations. This is adequate but not rich; a 3 is appropriate.

  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 purpose and then immediately provides usage routing. Every sentence 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?

  For a simple read-only tool with no required parameters, full schema descriptions, a provided output schema, and safety annotations, the description is complete. An agent can confidently select and invoke this tool based on the description alone; the schema covers invocation details.

  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 all four parameters (period, full_data, summarize, max_results) are fully documented in the schema. The description adds no parameter-level detail, which is acceptable under the baseline given the schema already handles this.

  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: 'Return general headline and top-news stories from Google News.' It also explicitly distinguishes this tool from siblings by noting it operates 'without a keyword or topic seed,' making its scope clear relative to the keyword, location, topic, and site tools.

  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 gives explicit when-to-use guidance: 'Use this for a broad news snapshot,' and explicitly routes users to alternatives when a filter exists: 'use the keyword, location, topic, or site tools when the user gives a filter.' This is clear routing with named alternative categories.

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

• get_trendsA
  4.4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, lowering the burden. The description adds valuable behavior beyond the schema: it returns normalized 0-100 interest scores rather than absolute search volume, and it emphasizes historical data rather than live trends. This helps set expectations without contradicting 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 sentences, each earning its place: the first states the core purpose, the second clarifies the usage context and output scale, and the third names the alternative for a different use case. It is front-loaded and free of 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?

  The tool has an output schema, full schema coverage, and read-only annotations, so the description does not need to explain return structures or safety. It covers key context: historical data, normalized scores, timeframe orientation, and the closest alternative. It does not discuss limitations such as keyword count or data availability, but those are minor given the schema and output schema.

  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 carries the parameter documentation burden. The description adds only the general notion that keywords should be 'known' and can be plural, which maps to the keyword parameter. That is a small increment over the schema, so 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 uses a specific verb ('Return'), names the exact resource ('historical Google Trends interest-over-time points'), and scopes to 'one or more known keywords'. It also differentiates from get_trending_terms by contrasting historical trajectory with what is trending now, so an agent can distinguish it from at least its closest sibling.

  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 the tool: 'for trajectory and comparisons across a timeframe.' It also gives a concrete alternative and exclusion: 'Use get_trending_terms for what is trending now.' This is clear routing guidance, not just an implied context.

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

• get_categoriesA
  4.5/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, so this is clearly a safe read-only operation. The description adds context that the tool provides authoritative category identifiers for use in other trend tools, but it does not disclose additional behavioral traits such as output volume, ordering, or whether categories are pre-defined or dynamic. Given the annotations cover the safety profile, a 3 is appropriate.

  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 no filler. The purpose is stated first, and the usage instruction is compressed into a direct, actionable second sentence.

  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 zero-parameter read-only lookup tool with an output schema and clear annotations, the description provides enough information for an agent to call it correctly. It states what is returned, why it is needed, and when to invoke it. Nothing essential is missing.

  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 0 parameters, so there are no parameter semantics to clarify. The baseline for no-parameter tools is 4, and the description does usefully explain that the returned IDs are intended for the cat parameter of other trend tools, which helps an agent understand how to use the results.

  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 ('Return'), a concrete resource (Google Trends category IDs and names), and its intended use (the cat parameter of trend tools). This clearly distinguishes it from sibling tools that retrieve news or trend data, so an agent can tell this is a lookup/reference tool.

  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 states when to call it: 'when a category filter is needed.' It also warns against guessing category IDs, which is actionable guidance that steers the agent toward this tool rather than improvising a category value.

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

• get_news_by_locationA
  4.5/5.0
  Behavior4/5

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

  Annotations already convey read-only, non-destructive, and open-world behavior. The description adds useful contextual behavior: it targets place-based Google News searches and emphasizes geography as the filter. It does not add details about return formatting, but the output schema covers that.

  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?

  Two sentences carry the essential purpose and usage routing with no filler. The core scoping statement is front-loaded, and the alternative-tool note is concise.

  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?

  The tool is simple, has full schema coverage, has annotations for safety, and has an output schema. The description sufficiently explains when to use it and how it differs from its sibling, so nothing critical is missing for correct invocation.

  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 every parameter is adequately documented in the schema itself. The description reinforces the location-centric purpose but does not need to repeat parameter semantics; 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 ('Find'), a specific resource ('recent Google News articles'), and a clear scope ('place-focused location such as a city, state, or country'). It also explicitly distinguishes this tool from get_news_by_keyword, so an agent can differentiate them immediately.

  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 gives clear when-to-use guidance: geography is the primary filter. It names the alternative tool, get_news_by_keyword, for general subject searches, making the routing decision explicit.

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

• get_ranked_trendsA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful context about the temporal nature ('currently trending') and the ranking semantics ('week-over-week growth or volume'), which clarifies behavior beyond the structured 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 two concise sentences: the first states the core function and ranking criteria, the second gives direct routing to alternatives. Every sentence earns its place and the most important information is front-loaded.

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

  Completeness5/5

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

  The description, combined with the fully documented schema and rich annotations, completely covers what an agent needs to know to call this tool correctly. The output schema and readOnly/openWorld hints fill in the rest, and the sibling references eliminate ambiguity about when to use 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%, so the input schema already documents all four parameters with defaults and allowed values. The description adds context that the tool ranks by 'growth or volume', which loosely maps to the sort parameter, but it doesn't provide any parameter-specific detail beyond what the schema already 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 clearly states the action ('Return') and the resource ('currently trending keywords'), with specific sorting criteria ('week-over-week growth or volume'). It also differentiates itself from sibling tools by naming get_top_trends and get_trends, so an agent can identify the correct tool without ambiguity.

  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 says when to use this tool ('when explicit ranked order matters') and names alternatives for other contexts: get_top_trends for a simpler current feed and get_trends for historical series. This gives clear routing guidance beyond just the tool's function.

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

• get_related_queriesA
  4.5/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint=true, openWorldHint=true, and destructiveHint=false, so safety is covered. The description adds useful behavioral context by specifying 'top and rising' and 'literal search queries', clarifying the result semantics beyond a generic query-list tool. No contradiction 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?

  Two concise sentences: the first front-loads the core function, the second provides routing guidance and alternatives. Every sentence earns its place, with no filler or redundant restating of 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?

  For a tool with 5 parameters, 1 required, a full output schema, and annotations covering safety, the description provides the core function, usage context, and sibling disambiguation. Nothing essential for selection or invocation 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 is 3. The description adds a minor nuance with 'one seed keyword', but parameter semantics are essentially fully documented in the schema; no additional compensation is needed.

  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 verb ('Return') and resource ('top and rising literal search queries related to one seed keyword'), and explicitly differentiates from sibling tools by naming get_related_topics and get_suggestions. This removes ambiguity about what the tool does.

  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 gives explicit when-to-use guidance ('Use this for query expansion') and names specific alternatives with conditions ('use get_related_topics for topic entities or get_suggestions for autocomplete candidates'). This is ideal routing information.

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

• get_suggestionsA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds behavioral context by framing the tool as lightweight and suggesting it exposes autocomplete-style entity candidates, which helps an agent set expectations for scope and response character beyond the structured 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?

  Two sentences with no filler. The core action and resource are front-loaded, and the alternative is mentioned in a single clear sentence. Every word 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?

  The tool has a simple two-parameter schema with full schema coverage, read-only annotations, and an output schema. The description fully covers the tool's purpose and the key sibling alternative, so there are no material 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?

  Schema description coverage is 100%, so the schema already documents 'keyword' and 'language' sufficiently. The description reinforces 'seed keyword' but adds no additional parameter semantics, so a baseline score 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 states a specific verb and resource: 'Return Google Trends autocomplete suggestions for a seed keyword.' It also distinguishes itself from the sibling get_related_queries by naming the exact difference in use case, making the tool's purpose 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 explicitly says when to use this tool ('lightweight autocomplete or entity candidates') and when to use get_related_queries instead ('top or rising demand signals'). This gives an agent clear decision criteria without needing to inspect other tool schemas.

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

• get_top_trendsA
  4.5/5.0
  Behavior4/5

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

  Annotations already establish readOnly, openWorld, and non-destructive behavior. The description adds meaningful context beyond that: the data source (Google Trends RSS), the 'bounded' nature of the feed, and the inclusion of related news where available. This is useful behavioral context without contradicting 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?

  Two sentences deliver the core purpose, data source, scope, and a sibling-tool routing note with no filler. The most important guidance is front-loaded before the alternative.

  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?

  Given a simple, fully documented schema, clear annotations, and an output schema, the description covers what an agent needs to select and invoke the tool correctly. No critical usage or exclusion information 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 schema already documents all three parameters (geo, type, limit). The tool description does not add new parameter-level meaning, so it is adequate at the baseline but not higher.

  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 resource ('Google Trends RSS'), a concrete action ('Return a bounded current topic discovery feed'), and the content scope ('current top or daily trends'). It also distinguishes itself from get_ranked_trends explicitly, making the tool's purpose unmistakable.

  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 gives direct usage direction: use this for current top or daily trends, and switch to get_ranked_trends when explicit ranking by growth or volume matters. This is clear, explicit guidance that helps an agent choose correctly among siblings.

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

• get_trending_termsA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is well covered. The description adds useful behavioral context by emphasizing that results are 'trending now' and that related news metadata may be included, which helps set expectations about the response. It does not contradict 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 two sentences with zero filler. The primary functional statement comes first, and the usage routing to get_trends comes second. Every sentence 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?

  For a tool with two optional parameters, a complete output schema, and annotations covering safety, the description is fully sufficient. It states what the tool returns, the geographic dimension, the optional news metadata, and when to use an alternative. Nothing needed for correct invocation 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 input schema already fully documents both geo and full_data parameters with detailed examples and defaults. The description adds only minimal semantic reinforcement by mentioning 'geography' and 'related news metadata,' but it does not need to compensate for any schema gaps. 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: 'Return terms that are trending now for a geography.' It also explicitly distinguishes itself from get_trends by clarifying that this tool is for current trend discovery while get_trends handles historical interest. This makes the tool's purpose immediately clear and differentiates it from at least the most similar sibling.

  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 gives explicit usage guidance: 'Use this for current trend discovery; use get_trends when the user wants historical interest over time for known keywords.' This directly tells an agent when to select this tool versus an alternative, leaving no ambiguity about the intended use case.

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