Server Quality Checklist

Tool Scores

• pagespeed_analyze_batchA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds meaningful context beyond annotations: it mentions progress notifications emitted when supported by the client and notes that results include success/failure counts. This gives the agent insight into execution behavior 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?

  The description is three sentences, each earning its place: purpose is front-loaded, followed by sibling routing, a practical example, and a behavioral note about progress notifications. There is zero fluff or redundancy, making it easy for an agent to parse quickly.

  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 six parameters with complete schema documentation, a robust output schema, and annotations covering safety (readOnly, idempotent, non-destructive), the description provides all necessary guidance for correct invocation. It covers usage, alternatives, an example, and a behavioral note—comprehensive for this tool's complexity.

  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 has 100% description coverage for all six parameters, including units, defaults, and constraints. The tool description adds no additional parameter-level guidance, but since the schema fully documents semantics, the baseline of 3 is appropriate. The description's mention of '1–10 URLs' aligns with schema constraints but adds no new 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 function: analyze 1–10 public URLs and return per-page results plus success/failure counts. It distinguishes itself from sibling tools by explicitly naming pagespeed_analyze_page for a single URL and pagespeed_compare_pages for direct comparison, making selection 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 explicit routing guidance: use pagespeed_analyze_page for one URL or pagespeed_compare_pages for direct comparison. It also includes a concrete example (triage ten highest-traffic landing pages) that grounds the tool in real usage, leaving no ambiguity about when to invoke it.

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

• pagespeed_analyze_pageA
  4.5/5.0
  Behavior4/5

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

  Annotations already mark the tool read-only, idempotent, and non-destructive. The description adds that the Google API is contacted and results may come from a local cache, setting expectations about external dependency and possible staleness. No contradiction with the annotations.

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

  Conciseness5/5

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

  Four short sentences: purpose, report-mode guidance, a concrete example, and an external-behavior caveat. Each sentence earns its place, and the core purpose 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 fully described schema, enums, annotations covering safety, and an output schema present, the only operational context an agent needs is report-mode selection and the external API/cache behavior — both provided. Nothing significant is missing for correct selection and invocation.

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

  Parameters4/5

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

  Schema coverage is 100%, so the baseline is 3. The description adds meaning by mapping report enum values to intended use cases and giving a concrete example ('analyze a mobile product page and return the three most useful remediation steps'), which clarifies strategy and report selection 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 opens with 'Run a PageSpeed Insights Lighthouse analysis for one public page' — a specific verb, resource, and scope. Saying 'one public page' differentiates it from batch and compare siblings, and the list of report modes clarifies its capabilities further.

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

  Usage Guidelines4/5

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

  The description gives explicit decision rules for the report parameter ('summary for a health check', 'recommendations for a prioritized fix list'), which tells an agent which mode fits a goal. It does not mention sibling tools by name, but 'one public page' implies single-page scope versus batch analysis.

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

• pagespeed_get_field_dataA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior; the description adds meaningful behavioral context by stating that it returns p75 field metrics or a clear no-data result, and by clarifying real-user field data rather than lab measurements. It does not mention rate limits or auth, but the annotations cover the safety profile.

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

  Conciseness5/5

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

  Four short sentences carry distinct information: purpose, parameter guidance, example, and return behavior. Every sentence earns its place, and the most important scoping guidance is front-loaded.

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

  Completeness5/5

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

  For an idempotent, read-only tool with a complete input schema and an output schema, the description covers the key decisions an agent must make: which URL/origin to query, what kind of metrics to expect, and what happens when no data exists. Nothing critical 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?

  Schema description coverage is 100%, so the baseline is 3. The description adds value beyond the schema by explaining when to choose page vs origin, specifically mentioning insufficient traffic, and by giving a concrete mobile LCP/INP example that helps ground the formFactor and metric concepts.

  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: get real-user Core Web Vitals from Chrome UX Report. It also explicitly distinguishes itself from Lighthouse lab measurements, which sets it apart from sibling analysis tools without needing to inspect 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 Guidelines4/5

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

  It gives concrete selection guidance for scope: page for one URL, origin for a bare origin when page traffic is insufficient. It also clarifies that this is not Lighthouse lab data, but it does not name a specific sibling tool like pagespeed_analyze_page as the lab alternative, so the routing is clear but not fully explicit.

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

• pagespeed_clear_cacheA
  4.7/5.0
  Behavior5/5

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

  Beyond the idempotentHint and destructiveHint annotations, the description adds valuable behavioral context: the cache is in-memory and process-local, later calls will contact Google again, and the tool does not alter the target website or remote data. This gives the agent a clear mental model of side effects.

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

  Conciseness5/5

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

  Three compact sentences, each earning its place: the first states the action and effect, the second gives the recommended trigger, and the third clarifies safety and non-destructiveness. The most relevant 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 zero-parameter tool with an output schema and no nested objects, the description fully covers what the agent needs to decide when to call it and what to expect. No critical behavioral or scoping details are 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 zero parameters, and schema description coverage is 100%, so there is nothing for the description to add about parameters. The baseline of 4 applies because the description correctly focuses on behavior instead.

  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 ('Clear') and resource ('this server process's in-memory PageSpeed response cache'), and explicitly contrasts the scope with other tools. This clearly differentiates it from sibling analysis tools like pagespeed_analyze_page or pagespeed_get_field_data.

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

  Usage Guidelines4/5

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

  The description gives an explicit use case: use after a deploy when a cached result is stale. It also states what it does not do, preventing misuse. However, it does not name specific alternatives or explicitly state when not to use it, leaving a small gap.

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

• pagespeed_compare_pagesA
  4.7/5.0
  Behavior5/5

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

  Beyond the destructiveHint annotation, the description discloses that baseline mode records the first call, warns to rely on guaranteed deltas rather than medians alone, and states that replaceBaseline overwrites local baseline state. This is meaningful behavioral transparency beyond what annotations provide.

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

  Conciseness5/5

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

  Three sentences with no wasted words: the first states the core purpose, the second gives operational guidance, and the third provides examples and the destructive state-change warning. The structure is front-loaded and easy to parse.

  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 an 8-parameter tool with full schema descriptions and an output schema, the description covers the key operational nuances: mode selection, first-call baseline behavior, run counts, examples, and state overwriting. Nothing critical for correct invocation 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?

  Schema coverage is 100%, so the baseline is 3. The description adds value by explaining the behavioral semantics of baseline mode's first call and why runs=3 or more is recommended, rather than merely repeating schema defaults.

  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: 'Compare two pages now' or 'measure one page against its locally stored baseline.' It clearly distinguishes the two modes and gives concrete examples, making the tool's purpose distinct from sibling tools like pagespeed_analyze_page.

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

  Usage Guidelines4/5

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

  It explains when to use pages versus baseline mode and provides practical examples such as comparing staging against production or verifying a deployed fix. It does not explicitly name sibling alternatives or exclusions, but the contexts are clear enough to route an agent correctly.

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

• pagespeed_diagnose_pageA
  4.7/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering safety and side-effect expectations. The description adds a meaningful behavioral constraint: 'exactly one diagnostic lens' and 'Returns focused evidence rather than a full Lighthouse dump', which aligns with and enriches the annotation profile. No contradiction exists.

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

  Conciseness5/5

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

  The description is three sentences of dense, useful information with zero fluff. It front-loads the core purpose, states the usage condition, and embeds a practical example in the same breath. Every sentence earns its place, making it highly efficient.

  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 that there is a full input schema, an output schema is present (per context), and annotations cover safety and idempotence, the description provides everything an agent needs to decide and invoke correctly: what it does, when to use it (vs. analyze), when not to, and a working example. 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?

  Schema description coverage is 100%, so all four parameters are fully documented in the schema itself (baseline 3). The description adds value by providing a concrete example ('focus=render-blocking to identify CSS/JS delaying first render') that clarifies the practical meaning of the focus parameter beyond its enum listing, which justifies a 4.

  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 ('Inspect') and resource ('one page') with a defined scope ('exactly one diagnostic lens'), and explicitly distinguishes itself from pagespeed_analyze_page by saying 'do not use it for a general score'. It also lists the available lenses, making the tool's purpose unambiguous and well-differentiated from siblings.

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

  Usage Guidelines5/5

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

  The description gives explicit when-to-use guidance: 'Use after pagespeed_analyze_page identifies a problem' and when-not-to-use: 'do not use it for a general score'. It even provides a concrete example (focus=render-blocking) to illustrate proper invocation, which is more than most tool descriptions offer.

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