Sitelemetry

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

Annotations already carry the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true). The description adds useful context beyond the annotations: the WCAG 2.2 edition, the fact that the analysis comes from the DOM, and the claimed output (violations with fixes). Notably, the wording 'static audit' is implied read-only, and that is not contradicted by the annotations but readOnlyHint=false warns the opposite; because the description never explicitly claims read-only, it is not a contradiction, though side-effect expectations stay fuzzy.

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

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

A tight single sentence front-loads the verb and scope, then a compact checklist of 8 audit areas, and closes with the return value. There is no filler and no repetition of the input schema; every phrase adds information.

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

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

For a two-parameter audit tool with a documented schema and an output schema, the description is nearly complete: it specifies the audit standard, the data source, the exact coverage, and the output type. It only omits a few meaningful details compared to an ideal spec, such as whether the entire domain is crawled or only a single page is audited, and whether any verification is needed before the run; these are left to the parameter description.

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

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

Schema coverage is 100%: target includes an example plus explicit ownership/authorization requirement, and lang comes with a complete enum and usage note. The description adds no parameter-level details beyond context, so the schema does the semantic heavy lifting; baseline 3 applies.

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

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

States a specific verb and resource: 'Static WCAG 2.2 accessibility audit' and enumerates the exact checks performed (image alt text, form labels, heading structure, landmarks, color-contrast signals, language attribute, duplicate ids, iframe titles). This cleanly distinguishes it from sibling audit tools (audit_seo, audit_performance, audit_security, etc.) without needing to inspect them.

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

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

The applicability is implied: it is the accessibility-audit tool among the audit_ siblings, so an agent can infer when to pick it. However, the description never explicitly states when to use it instead of audit_full, or notes conditions such as needing an authenticated page to audit. Usage context is clear but not directly spelled out.

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

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

Beyond the annotations, the description adds behavioral context: the audit examines defined AI signals and returns findings with fixes. The target parameter also adds an important authorization constraint, and the read-only/destructive profile is already covered by annotations.

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

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

The description is compact, front-loaded with the core purpose, and uses a tight list for audit dimensions without filler. Every sentence adds value.

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

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

The definition covers what is audited, what results to expect, the authorization requirement, and optional report language. Since an output schema exists, the single mention of 'Returns findings with fixes' is sufficient.

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

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

Schema coverage is 100%, so both target and lang are already clearly documented with defaults, enums, and examples. The description does not need to add parameter-specific detail because sender the schema does the heavy lifting.

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

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

The description states a specific action ('Assess how visible and citable a site is to AI search and LLMs') and names concrete dimensions it covers, such as entity clarity, answerability, and llms.txt/AI-crawler policy. This makes it immediately distinguishable from sibling audit tools like audit_seo and audit_accessibility.

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

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

The intended use case is clear: run this when auditing a site's AI search and LLM visibility in a GEO/AEO context. It does not explicitly name exclusions or alternative audit tools, but the AI/LLM framing is explicit enough to guide selection.

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

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

Annotations include readOnlyHint=false, openWorldHint=true, and destructiveHint=false. The description adds useful behavioral detail: runs pillars in parallel and returns a blended grade plus additional summaries. However, it does not clarify what kind of side effects or writes might occur despite readOnlyHint=false, and it doesn't mention any authentication/rate-limit backend. Not a contradiction but a minor gap.

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

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

Two sentences, no filler. The first sentence front-loads the pillars and all key outputs; the second gives a concrete use case. Every sentence contributes.

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

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

With an output schema available, the description doesn't need to list every field. It covers scope (all pillars), what is returned, and when to choose this tool. It could also mention that a full audit is heavier than running one pillar, but the "full" name and sibling tool list already hint at that tradeoff.

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

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

Schema coverage is 100%; both 'target' and 'lang' already have descriptive text. The tool description adds no new parameter-specific meaning beyond operating on a URL and report language. That is sufficient given the schema does the heavy lifting.

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

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

The description uses a specific verb 'Run' with an explicit resource: all six audit pillars in parallel. It clearly enumerates the pillars and the deliverables (blended grade, each pillar summary, prioritized cross-pillar findings with evidence and fixes), making the tool unmistakably distinct from the single-pillar sibling tools.

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

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

The description states when to use it: 'Best for a complete health check or an audit-fix-retest loop.' This gives a clear context, though it doesn't explicitly say 'use the individual audit_* tools when only one pillar is needed.' The sibling names and 'full' tag imply the trade-off.

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

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

With annotations already covering safety (destructiveHint=false) and open-world behavior, the description adds useful behavioral context: the audit is derived from site HTML and headers, and it returns gaps plus fixes. It does not go into rate limits or authorization caveats, but the parameter description already flags authorized targets, so this is reasonably transparent.

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

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

The description is a single dense sentence with the main purpose at the front and a compact 'Returns gaps + fixes' at the end. It is longer than strictly necessary, but every part contributes meaningful scope detail.

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

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

With full parameter descriptions, output schema present, and annotations exposing safety behavior, the description is sufficient for an agent to understand what the tool covers and what it returns. It does not explicitly mention limitations, such as only client-side detection, but that is a minor gap.

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

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

Input schema coverage is 100%: target and lang are both described with clear meaning, and lang has an explicit enum. The main description adds little parameter-level detail beyond the schema, so the baseline score of 3 is appropriate.

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

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

The description states a specific verb and resource: it detects and audits the analytics, tag, marketing-pixel, verification, and consent stack from the site HTML and headers. The explicit list of technologies (GA4, GTM, Meta Pixel, etc.) clearly distinguishes it from the other audit_* sibling tools.

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

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

The description gives clear context about the tool's specialty: analytics, tags, pixels, consent/CMP, and dataLayer leaks. It does not explicitly name sibling tools or say 'use this instead of audit_security,' but the tightly scoped wording makes the intended use apparent. Slight deduction because there is no explicit when-not-to-use guidance.

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

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

The description adds useful behavioral context beyond the annotations: it uses Google PageSpeed Insights, combines Lighthouse lab data with CrUX field data, returns improvement opportunities with fixes, and uses the operator PAGESPEED_API_KEY when set. No statement contradicts the annotations, though it does not discuss failure modes like missing keys or rate limits.

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

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

The description is compact and front-loaded. It states the action, names the metrics, summarizes the output, and records the key environment variable note in just a few sentences with no padding.

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

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

Given the complete input schema, output schema, and existing annotation hints, the description provides sufficient context for an agent to select and invoke this tool. It covers the essential external dependency, the metric scope, and the expected result format.

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

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

The input schema already has 100% parameter coverage, including descriptions for target, lang, and strategy. The tool description adds general context but no new per-parameter meaning beyond what the schema provides, so the baseline score of 3 is appropriate.

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

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

The description clearly states the action: measure performance via Google PageSpeed Insights, and it names the specific metrics (LCP, INP, CLS, FCP, TTFB). This makes it easy to distinguish from the sibling audit tools for accessibility, AI visibility, SEO, security, and integrations.

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

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

The intended use case is obvious from the title and metric list: this is the performance/Core Web Vitals audit. It does not explicitly name sibling alternatives or exclusion criteria, such as when to use audit_full instead, so it stops short of full routing guidance.

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

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

The description meaningfully supplements the annotations by explaining the default passive-only behavior, the distinction between account-available and protected modules, and the requirement that active scanning be operator-enabled. This is valuable behavioral context beyond readOnlyHint=false and destructiveHint=false.

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

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

The description is information-dense yet compact. It front-loads the core purpose, then covers default behavior, module policy, active-scan restrictions, and output shape in only two sentences. Every clause contributes useful selection or invocation information.

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

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

The description covers target authorization, default behavior, module categories, active-scan availability, and output semantics. It does not enumerate which of the 27 modules are protected vs. account-available vs. active, and that mapping would be useful, but because the schema exposes the module list, the description is still reasonably complete.

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

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

Schema coverage is 100%, so the baseline is strong. The description adds extra meaning beyond the schema by explaining the default public-signal posture, module authorization categories, and the operator gating on active scans. This helps an agent reason about module selection without simply repeating property names.

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

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

The description opens with a specific verb and resource: 'Run a security posture audit of a website you own or are authorized to assess.' This clearly identifies what the tool does and separates it from sibling audit tools like audit_performance, audit_seo, and audit_accessibility.

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

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

The description gives concrete guidance on when the tool applies (owned/authorized targets), what the default audit includes, and how to opt into additional modules. It does not explicitly say when to use another sibling tool, but it does provide clear authorization and activation gating.

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

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

The description states the core behavior: it crawls a website, performs technical SEO checks, returns prioritized findings with fixes. Since annotations already are safe (destructiveHint=false), this adds useful detail and clearly sets expectations about the activity. However, it does not discuss rate limits, negative side effects on the target, or authorization requirements beyond what the target parameter mentions, so it is adequate but not deeply transparent.

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

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

The description is two tight sentences: the first states the action and the full checklist, and the second states the result. There's no filler, no repetition of schema details, and the content is front-loaded. The comma-separated enumeration is efficient for an agent to parse.

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

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

For a complex auditing tool, the description covers the core domain and enumerates the full audit surface. With an output schema present and full parameter documentation in the schema, this is nearly sufficient. The only notable gap is not explicitly naming alternatives (e.g., audit_full) or how to decide between them, but that's a minor context gap.

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

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

The input schema already provides complete descriptions for all three parameters, including the default values, allowed language enum, and maxPages bounds. The description's text doesn't need to repeat this and simply gives context for 'target' by saying 'Crawl a site'. At 100% schema coverage, the description adds almost no parameter-level value, so the baseline score of 3 is appropriate.

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

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

The description opens with a specific verb and resource ('Crawl a site and audit technical SEO') and enumerates a detailed set of concrete checks (crawlability, indexation, titles/meta, canonical, structured data, broken links, redirect chains, AI-crawler policy). This clearly defines the tool's domain and distinguishes it from sibling tools like audit_security or audit_accessibility, making the intended scope unambiguous.

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

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

The description clearly establishes when to use it: for a technical SEO audit, including a specific set of sub-audits. It does not explicitly name alternatives or exclusion criteria, but the scoping language is clear enough that an agent can match a user request to this tool versus the other audit-focused siblings.

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