Server Quality Checklist

Tool Scores

• get_advanced_search_analyticsC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. It mentions the tool filters and returns analytics, but does not disclose data lag (e.g., results trailing by 2 days), potential rate limits, pagination behavior beyond 'pagination' mention, or whether data is aggregated. The description is too minimal to convey these operational traits.

  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 a single dense sentence that front-loads the core purpose ('Search analytics with full control') and quickly enumerates the main capabilities. It is efficient with no filler, though slightly long due to the enumeration. Structurally it is clear and scannable.

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

  Completeness2/5

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

  Given the tool's complexity (16 parameters, 6 enums, multiple filters), the description is notably incomplete as a standalone guide. It does not mention that only siteUrl is required, that date ranges can be specified via days or start/end dates, that defaults exist, or that filter operators are available. The schema covers these, but the description should provide an overview to help an agent decide initially whether this tool fits; it doesn't.

  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 100% parameter descriptions, so the description adds little beyond summarizing the existing parameters. It lists filter types and options that map directly to schema fields, but does not introduce new semantics or clarify edge cases. Baseline 3 is appropriate given high schema coverage.

  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 that this tool provides search analytics and highlights its advanced filtering and control options (country, device, query, page, search type, aggregation, data state, pagination). It distinguishes itself from the simpler 'get_search_analytics' by emphasizing 'full control', so the purpose is unambiguous and not a tautology.

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

  Usage Guidelines2/5

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

  There is no explicit guidance on when to use this tool versus siblings like 'get_search_analytics', 'get_performance_overview', or 'compare_search_periods'. The description implies advanced use but does not state when to prefer it over alternatives or under what conditions it is inappropriate. An agent would have to infer usage context.

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

• compare_search_periodsB
  3.2/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden. It mentions the output includes overall totals and optional breakdowns, but does not disclose behavioral traits such as whether it requires authentication, how it handles missing data, or any rate limits. It also doesn't clarify the meaning of 'biggest movers' or the sorting behavior beyond the rowLimit parameter description.

  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 a single, concise sentence that front-loads the core purpose and mentions the optional breakdown. It is efficient and avoids redundancy, though it could be slightly more structured with a second sentence for usage guidance.

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

  Completeness3/5

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

  Given the tool has 7 parameters and no output schema, the description provides a reasonable overview but lacks details on return format, error handling, or specific behavioral expectations. The schema covers parameter semantics, but the description does not fully compensate for the absence of annotations and output schema, especially for a comparison tool that might have complex output.

  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 context about the overall comparison and optional dimension breakdown, but does not add significant meaning beyond the schema. The rowLimit parameter is described in the schema, and the description's mention of 'biggest movers' aligns with the schema's 'sorted by biggest click change'.

  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 tool compares search performance between two time periods, including overall totals with absolute and percentage changes, plus an optional per-dimension breakdown. It distinguishes itself from siblings like get_search_analytics and get_performance_overview by focusing on period comparison, though it doesn't explicitly name a sibling alternative.

  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 description implies usage for comparing two periods but does not explicitly state when to use this tool versus alternatives like get_search_analytics or get_performance_overview. It lacks explicit exclusions or conditions that would guide an agent to choose this tool over others.

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

• get_search_analyticsB
  3.3/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It does reveal the returned metrics and that omitting dimensions yields both top queries and top pages. However, it does not describe the output structure, pagination, or how the results are organized when dimensions are supplied, leaving some behavioral ambiguity.

  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 sentence front-loads the core action and result metrics, and the second sentence usefully clarifies the default dimension behavior.

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

  Completeness3/5

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

  The description plus fully documented schema provide enough to make a basic call correctly. However, with no output schema, the description should explain the shape of the returned data more fully; it names metrics but not whether the response is a flat list, grouped arrays, or paginated.

  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%, and the schema already documents every parameter thoroughly, including date-lag behavior and siteUrl format. The description's only added parameter insight is the default behavior for the `dimensions` array, but the schema already states 'Omit to get both top queries and top pages.' Thus the description adds little beyond the schema.

  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 names a specific verb and resource ('Get top search queries and pages') and the metrics returned (clicks, impressions, CTR, average position), so an agent can tell what the tool does. It also notes the default grouping behavior, but it does not explicitly contrast this tool with sibling tools like get_advanced_search_analytics or get_search_by_page_query.

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

  Usage Guidelines2/5

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

  There is no guidance about when to choose this tool over alternatives such as get_advanced_search_analytics or get_performance_overview. The description implies it is for search analytics reporting, but it never states prerequisites, exclusions, or conditions that would route an agent to a sibling tool.

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

• batch_url_inspectionB
  3.4/5.0
  Behavior2/5

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

  No annotations are provided, so the description must disclose behavioral traits itself. It mentions that it 'return[s] crawl/index status' but omits any details about rate limits, partial failures, authentication requirements, or how invalid URLs are handled. The silence on side effects (even though inspection is likely read-only) is a notable 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?

  A single, compact sentence that conveys the core action and result without filler. However, it is slightly too sparse—users may need a bit more context about the returned statuses—but for a simple tool, this level of conciseness is appropriate.

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

  Completeness3/5

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

  With no output schema, no annotations, and only a terse description, the agent lacks clarity on what 'crawl/index status' actually looks like, whether errors are returned per-URL or as a single failure, and any side effects. The description is adequate for a basic call but insufficient for robust error handling or formatting expectations.

  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 description adds little beyond what the schema already documents for siteUrl and urls. It does clarify the return meaning ('crawl/index status'), but that is behavioral, not parameter-specific. The max of 10 URLs is already in the schema, so the description provides only marginal added 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 uses a specific verb ('Inspect') and a clear resource ('URLs'), and immediately states the batch capacity ('up to 10 URLs at once'). This distinguishes it from the single-URL sibling tools like inspect_url_enhanced, 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 Guidelines3/5

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

  The description implies a batch use case ('at once') but gives no explicit guidance on when to choose this tool over inspect_url_enhanced or other alternatives. It lacks exclusions, prerequisites, or conditions for use, leaving the selection logic implicit.

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

• get_performance_overviewB
  3.4/5.0
  Behavior2/5

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

  With no annotations, the description must bear the full weight of behavioral disclosure. It does not mention the 2-day data lag for Search Console, the read-only nature, normalization, or any error/edge cases. The lag is only hinted in the 'days' parameter description, not in the main description, so an agent calling this tool with default parameters may not realize results are stale by two days. This is a significant gap for a data-returning tool.

  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?

  A single, front-loaded sentence with no filler. It states the essence (summary of search performance) and lists the three concrete output components, which is efficient and scannable. Nothing extraneous.

  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?

  Although there is no output schema, the description explicitly names the content of the response (totals, daily trend, top 5 queries/pages), which gives an agent a clear expectation of return shape. It omits any mention of error handling or data availability caveats, but for a summary tool the essential information is present. The description is adequate for a tool of this simplicity.

  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% and each parameter has a useful description. The tool description adds nothing beyond the schema about how to specify the period, and it doesn't clarify relationships between days and start/end dates. Since the schema already covers this, the description's lack of extra param context is acceptable, but it also fails to reiterate the key caveat about the trailing window ending two days ago. Thus it doesn't add meaning beyond the schema, earning the baseline 3.

  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 uses a clear noun phrase ('Summary of site search performance') and enumerates specific deliverables (totals, daily trend, top 5 queries/pages), which makes the purpose obvious. It doesn't explicitly differentiate from siblings like get_search_analytics, but the 'summary' framing and the limited top-5 output imply a high-level view, so it's mostly identifiable even without naming alternatives.

  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?

  No explicit guidance on when to prefer this tool over get_search_analytics or compare_search_periods. The description implies a high-level overview use case, but the absence of any 'when to use' or 'alternative' note leaves the agent to infer from the feature list. That is implied usage rather than explicit guidance.

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

• get_search_by_page_queryB
  3.4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries some burden, but it discloses a key behavioral trait: the data lags by 2 days (implied via the 'days' parameter description, not directly in the main description). The main description itself is minimal, but the schema's parameter descriptions provide important context about default behavior (28 days) and data lag. Since the tool is a read-only query operation, the main description doesn't disclose mutation or side effects, but that's expected. It could mention that results are limited by rowLimit (though that's in schema). Given no annotations, the description does not add much beyond basic scope.

  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 a single, efficient sentence that covers purpose and key outputs without fluff. It is front-loaded with the core action. No unnecessary words. It earns a high score for conciseness, though it could slightly improve by adding a hint about when to use it, but that would lengthen it.

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

  Completeness3/5

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

  Given the tool's moderate complexity (6 params, 2 required) and high schema coverage, the description is adequate but not complete. It covers the purpose but lacks explicit guidance on parameters like date handling (though schema covers it) and doesn't explain what the output structure looks like (though no output schema exists). Since the schema is rich, the description doesn't need to re-explain everything, but a sentence about typical use cases would improve completeness. Overall, it's sufficient for an agent to call correctly if it reads the 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 already fully documents all six parameters, including the crucial 'siteUrl' format (URL-prefix vs sc-domain) and the date behavior. The description adds no additional parameter meaning beyond what the schema provides. For a tool with high schema coverage, baseline 3 is appropriate. The description doesn't need to repeat schema details.

  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 a specific verb ('Get'), resource ('search queries'), and scope ('traffic to one specific page'), and lists the metrics returned (clicks, impressions, CTR, position). It distinguishes from sibling tools like get_search_analytics by focusing on a single page's queries, though it doesn't explicitly name a sibling. It is clear and specific enough for an agent to understand its core function.

  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 description implies usage for page-level query analysis, but provides no explicit guidance on when to use this tool versus alternatives like get_search_analytics or get_advanced_search_analytics. It doesn't state any exclusions or conditions. The context makes it obvious it's for one page, but an agent might not know if this is the best tool for, say, detailed query analysis across a site.

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

• get_site_detailsA
  3.5/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of disclosing behavior. It does not mention that this is a read-only operation, any authentication or access prerequisites, rate limits, or error conditions. The phrase 'Get details' implies a safe read but fails to disclose potential side effects or required permissions, leaving the agent without crucial context.

  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 a single, efficient sentence with no unnecessary words. It front-loads the core purpose and specifies the key details, achieving maximum conciseness without sacrificing clarity.

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

  Completeness3/5

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

  Given the tool has one parameter, no output schema, and no annotations, the description gives a reasonable overview but lacks specifics about the response structure or any edge cases. It indicates verification and permission level, which hints at the output, but does not specify how the result is returned (e.g., as fields, booleans, etc.). For a tool this simple, it is adequate but not fully 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?

  The schema already describes the siteUrl parameter thoroughly (URL-prefix vs domain format), and coverage is 100%. The description adds no additional parameter semantics beyond what is in the schema, so the baseline of 3 is appropriate without any extra contribution.

  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 verb 'Get' and the resource 'details about a specific Search Console property', then specifies the details (verification status and permission level). This distinguishes it from sibling tools like list_properties (list all properties) and performance analytics tools, so an agent can immediately understand the tool's scope.

  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 description implies usage for a single property when you need verification or permission details, but it does not explicitly contrast with alternatives. It does not say when NOT to use it (e.g., when you need a list of properties), leaving that inference to the agent. Guidance is implicit rather than explicit.

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

• manage_sitemapsA
  3.5/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the burden. It does not mention side effects (e.g., submit/delete modify state), required permissions, or potential errors. The description only lists actions without disclosing behavioral implications, leaving the agent uninformed about consequences.

  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 a single, concise sentence that efficiently conveys the tool's purpose without unnecessary verbosity. It front-loads the main actions and is easy to parse.

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

  Completeness3/5

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

  The description is adequate for understanding the tool's function, but it lacks details about the return format or response structure. Since there is no output schema, the agent is left to assume typical behavior (e.g., success/error codes, status objects), which is a minor gap for correct usage.

  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 provides descriptions for all three parameters (action, siteUrl, feedpath) with 100% coverage. The tool description does not add any extra meaning beyond what the schema states, so it meets the baseline but does not enhance 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 clearly states the verb-resource combination: manage sitemaps. It explicitly lists the three actions (submit, delete, get status) and distinguishes itself from sibling tools like get_sitemaps or list_sitemaps_enhanced by focusing on single-item operations and modifications.

  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 description implies when to use the tool (for submitting, deleting, or fetching a specific sitemap status) but does not explicitly contrast it with alternatives like get_sitemaps for listing all sitemaps. Since sibling tools exist, more explicit guidance on when not to use this tool would be clearer.

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

• check_indexing_issuesA
  3.6/5.0
  Behavior3/5

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

  With no annotations, the description must carry the behavioral burden, and it does disclose that the tool is read-oriented, returns a summary and per-URL diagnosis, and covers specific problem categories. It does not mention caveats such as how many URLs are processed, whether results are cached, or possible failure modes, so transparency is acceptable but not strong.

  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 a single well-structured sentence that leads with the action, states the object and diagnostic categories, and closes with the expected return format. Every phrase earns its place with no repetition or 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?

  Input parameters and output forms are covered well: the schema covers the required parameters, and the description explains that the output will be a summary plus per-URL diagnosis. Given the lack of an output schema, it would be even more helpful to specify the exact response fields, but enough context is present for an agent to successfully invoke and interpret the 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 properties are already fully documented. The description adds only a general reference to multiple URLs but does not contribute new parameter-level meaning, which aligns with the baseline score for high schema coverage.

  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 names a specific operation ('Check multiple URLs'), a concrete resource domain ('indexing problems'), and elaborates with recognizable diagnostics such as blocked by robots.txt, noindex, and canonical mismatches. It is clear and differentiable from single-URL inspector tools, though it does not explicitly distinguish itself from the sibling batch_url_inspection.

  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 phrase 'multiple URLs' implies the tool is intended for bulk checks, and the focus on indexing problems suggests when to consider it. However, it does not explicitly state when to prefer this tool over similar siblings or provide exclusion criteria or workflow conditions.

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

• get_sitemapsA
  3.6/5.0
  Behavior4/5

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

  The description proactively lists the returned fields (path, last submitted/downloaded, pending status, error and warning counts), providing clear expectations without relying on annotations. It implies a read-only operation, which is appropriate for a 'get' verb, though it doesn't explicitly state side-effect-free behavior or required permissions. Given no annotations exist, the description effectively covers 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 a single, well-crafted sentence that begins with the verb and places important output context in parentheses for quick scanning. It contains no unnecessary words or redundancy.

  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 straightforward listing operation with one parameter, the description is largely complete, covering both the input context and the output expected. The only notable gap is the lack of distinction from the 'enhanced' sibling, which could be important for an agent deciding between them, but this does not undermine the core completeness for the tool itself.

  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 includes a detailed description of the siteUrl parameter, achieving 100% schema coverage. The tool description adds no additional parameter-level detail, so the neutral baseline applies.

  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 action 'List all sitemaps submitted for a property' and includes specific output fields in parentheses, making the purpose immediately obvious. However, it does not distinguish itself from the sibling tool 'list_sitemaps_enhanced', so it doesn't fully meet the bar of distinguishing 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 Guidelines2/5

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

  There is no guidance on when to use this tool versus alternatives like 'list_sitemaps_enhanced' or 'manage_sitemaps', nor are exclusions or prerequisites mentioned. The usage context is only implied by the description itself, leaving the agent without explicit decision support.

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

• inspect_url_enhancedA
  4/5.0
  Behavior4/5

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

  Without annotations, the description carries the full burden. It transparently lists the output fields (verdict, coverage state, etc.) and implies a read-only operation with no side effects. However, it does not mention potential errors, rate limits, or the exact response format.

  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 a single, concise sentence that efficiently enumerates the key output aspects. It is well-structured and free of unnecessary details.

  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 that no annotations are provided, the description provides a solid overview of the output contents. It lists the specific data points returned, which is sufficient for an agent to understand the tool's functionality. It could mention the response envelope or error handling, but the core purpose is well covered.

  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 provides complete descriptions for all three parameters. The tool description does not add any additional semantic meaning beyond the schema, so it does not enhance 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 clearly states the tool's purpose: providing detailed crawl and index status for a single URL, listing specific aspects like verdict, coverage state, robots.txt, canonicals, last crawl time, rich results, and mobile usability. It distinguishes itself from batch inspection tools by explicitly mentioning 'one URL'.

  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 description does not explicitly state when to use this tool over alternatives like batch_url_inspection or check_indexing_issues. It implies a single-URL use case but lacks explicit comparative guidance.

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

• list_propertiesA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden. It states that the tool lists properties but does not explicitly mention whether it is read-only, if it requires special permissions, or if there are any side effects. Since listing is inherently read-only, the description is acceptable but could be more transparent.

  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 a single, concise sentence that directly conveys the tool's function without any fluff or redundant information. It is perfectly sized for quick comprehension.

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

  Completeness3/5

  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 indicate what the tool returns. It mentions 'with permission levels', which gives some insight, but it does not specify the exact structure (e.g., list of objects, pagination, fields beyond permissions). The description is sufficient for basic understanding but lacks detailed return format information.

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

  Parameters5/5

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

  The tool has no parameters, and the schema is fully covered (100%). The description correctly implies that no parameters are needed, and there is nothing to explain. This is a case where the absence of parameters makes the description complete.

  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 purpose with a specific verb ('List') and scope ('all Google Search Console properties the authenticated account can access'), and it includes the additional detail about permission levels. This leaves no 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 Guidelines3/5

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

  The description does not explicitly mention when to use this tool versus alternatives, such as when to use get_site_details or get_search_analytics. However, the purpose is straightforward and self-evident for listing all properties, so the lack of explicit guidance is acceptable but not ideal.

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

• list_sitemaps_enhancedA
  4/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden of explaining behavior. It discloses the kind of information returned (errors, warnings, type, counts) and the optional child-listing behavior when sitemapIndex is provided. It does not mention error handling or response format, but the core behavior is transparent.

  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 well-structured, consisting of two clear sentences without any redundant or promotional content. It efficiently conveys the primary function and the optional parameter behavior.

  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 description provides sufficient context for the tool's expected output (detailed sitemap information with specific fields) and the optional child-listing mode. It does not describe pagination, error cases, or the exact shape of the response, but given the absence of an output schema, it is reasonably complete for most use cases.

  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?

  Both parameters are fully described in the schema with clear semantics. The tool description adds minimal additional context beyond referencing the optional sitemapIndex parameter, so it does not significantly enhance the schema's already comprehensive parameter information.

  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 purpose: to list detailed sitemap information including errors, warnings, type, and per-content-type counts, with an optional child-listing capability. It is distinct from sibling tools like get_sitemaps and manage_sitemaps, which are simpler or management-oriented.

  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 description implies usage for obtaining more detailed sitemap data than the basic get_sitemaps, but it does not explicitly state when to choose this tool over siblings. The optional child-listing behavior is mentioned, but there is no direct guidance on when not to use it or alternatives.

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

• reauthenticateA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral burden. It discloses a destructive effect (discarding stored credentials), the interactive browser flow, and the up-to-5-minute wait. It could add what happens on timeout or failure, but the core behavior is well covered.

  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 short sentences front-load the primary action, then give use cases and behavior. Every sentence carries information, and there is no filler or repetition.

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

  Completeness4/5

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

  For a parameterless tool with no output schema, the description covers what it does, when to use it, and how it behaves. It does not specify return values or failure modes, but those are less critical for an interactive reauthentication action.

  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?

  There are zero parameters and schema coverage is 100%, so there is nothing for the description to add about arguments. The baseline of 4 applies because no parameter documentation 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 identifies a specific verb-resource pair ('Discard stored Google credentials and re-run the OAuth browser login') and clearly differentiates this tool from the read/analytics siblings by addressing authentication state rather than data retrieval. The intent and mechanism are unambiguous.

  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 explicitly states when to use it: 'Use this to switch Google accounts or fix authentication errors.' It does not mention alternatives or exclusions, but no sibling provides this reauthentication function, so the context is sufficient.

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

• get_capabilitiesA
  4.5/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses that the tool enumerates available tools and reports authentication status, accurately describing a read-only discovery operation. No side effects are expected, and the description fully covers the 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?

  Two concise sentences with the action front-loaded. The first sentence states the core functionality, and the second adds a clear usage recommendation without any 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?

  For a zero-parameter discovery tool with no output schema, the description fully specifies what it does and when to call it. An agent can invoke it correctly with no further information.

  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 accepts zero parameters, so the description rightfully adds no parameter-specific information. The schema already covers all (zero) parameters, and the baseline of 4 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 uses a specific verb 'List' and a clear resource: every tool the Google Search Console server offers, plus authentication status. This clearly distinguishes it from siblings like list_properties, which lists properties rather than 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?

  Explicitly instructs to call this tool first when unsure what is available, providing a clear when-to-use context. It doesn't mention when-not-to-use or name alternatives, but for a discovery tool this is sufficient guidance.

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