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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds useful operational context (no API key required, read-only network check) and enumerates the exact inspection surfaces. It stops short of describing rate limits, failure modes, or return shape, so it improves on but does not fully exploit the behavioral space.

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 purpose is front-loaded and the exclusion guidance follows cleanly in a compact three-sentence block. It is somewhat acronym-dense (ARD 1.0, OAI-SearchBot, /.well-known paths), which increases reading cost without strictly earning its place for tool selection.

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?

There is no output schema, so the description should ideally hint at what the audit returns; it lists the checked dimensions but not the report structure. Still, for a one-parameter read-only diagnostic it gives enough for correct invocation, with return-shape disclosure the only notable 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?

Schema coverage is 100% for the single url parameter, so the schema already documents accepted forms and the HTTPS-default behavior. The description adds no parameter syntax beyond what the schema provides; 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 (audits) and resource (website URL/domain) and enumerates the exact checks performed (GPTBot access, RAG truncation, llms.txt, JSON-LD, Lighthouse agentic browsing). An agent can distinguish this from the sibling extraction and manifest-generation tools without opening any schema.

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?

Explicitly says to use this tool first when diagnosing why a site is omitted or misquoted by ChatGPT/Perplexity/Claude, and names two concrete exclusions with the correct alternatives (extract_byte0_markdown, generate_ai_manifests). When-to-use, when-not-to-use, and alternatives are all present.

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 already declare readOnlyHint=false, destructiveHint=false, idempotentHint=true, openWorldHint=false, so safety posture is covered by structured data. The description usefully adds that files are actively written into public/ or targetDir and enumerates what is scanned, but is silent on the key write risk: whether an existing /llms.txt or ai-catalog.json is overwritten, merged, or skipped.

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?

Front-loaded with the audit-and-generate purpose, and every clause carries substantive detail (category count, file types, artifact names). It is a single dense sentence with a heavy nested parenthetical, which costs a bit of readability but not enough to be wasteful.

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 no output schema, the description must carry the burden of explaining what comes back, and it only gestures at '6 weighted categories' without describing the report shape (scores, violations, per-category breakdown) or how results differ when outputAll is true. Adequate to call the tool, incomplete for interpreting its return.

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 description coverage is 100%, so both parameters (outputAll, targetDir) are already documented with defaults and examples. The description restates the generation behavior that outputAll controls but adds no syntax or edge-case detail beyond the schema, so the 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?

Specific verb+resource: a local structural compliance audit across named categories (robots.txt vs 14+ AI crawler directives, Schema.org JSON-LD in HTML/TSX/JSX, /llms.txt syntax, /.well-known/ai-catalog.json) plus generation of two artifacts. The scope is concrete and the title reinforces it, but nothing distinguishes it from siblings 'audit_ai_readiness' or 'generate_ai_manifests', which sound like overlapping capabilities.

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?

'Local filesystem' implies usage context, and the description makes clear it both audits and writes files. However, there is no guidance on when to pick this over 'audit_ai_readiness' (audit-only?) or 'generate_ai_manifests' (generation-only?), and no prerequisites (e.g., project must have a robots.txt or Next.js-style public dir) are stated.

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 already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered; the description adds real context beyond that — HTTP-only extraction, no API key required, output shape (GFM with front-loaded Schema.org tables) and the token-limit rationale. It stops short of error behavior or failure modes, so not a 5.

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?

Three sentences, each doing distinct work: what it produces, when to use it, and when not to. The output format and scope are front-loaded before the alternative-tool exclusion.

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?

No output schema exists, so the description must explain the return value — and it does, specifying clean GFM with Schema.org tables and the 25k-token truncation bound. Combined with the no-API-key and read-only notes, an agent has everything needed to call it correctly.

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?

Single parameter with 100% schema description coverage, including an example URL, so the schema does the heavy lifting. The description adds no further parameter syntax or constraints, making the baseline 3 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?

States a specific verb (strips/extracts) and resource (clean Byte-0 GFM Markdown from a URL), and enumerates exactly what is removed (hydration scripts, Liquid/WordPress bloat, inline SVG/CSS). It also names the sibling it is not (audit_ai_readiness), so an agent can discriminate without opening either schema.

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?

Gives both sides: use it when you need to read a page or pricing table inside an LLM context window without hitting the 25,000-token truncation limit, and explicitly says not to use it for a readiness score or robots.txt check, routing to audit_ai_readiness. When/when-not/alternative are all present.

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 already declare readOnlyHint, openWorldHint, idempotentHint and destructiveHint=false, so the safety profile is covered structurally. The description still adds useful context beyond that: no API key required, remote servers are not modified, and the output is 'ready-to-save' (i.e., synthesized content rather than a write). It does not describe return format or caching, so it is not exhaustive.

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?

Four sentences, purpose front-loaded in the first, with usage and exclusion rules following. Information-dense with no filler, though the opening sentence carrying three artifact types is heavy and slightly harder to scan than a bulleted form.

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 single-param, read-only synthesis tool with strong annotation coverage, the description covers what is produced, when to use it, alternatives, and auth requirements. The only gap is what the caller receives (raw file contents vs. counts/paths), though 'ready-to-save' partially implies this and no output schema exists to cover it.

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?

Only one parameter (domain) and schema coverage is 100%, with the schema itself documenting accepted forms ('example.com' or 'https://example.com'). The description adds 'from a live domain', reinforcing that it is fetched live rather than passed as content, but adds no syntax beyond the schema. Baseline 3 for high coverage 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?

Names a specific verb (compiles) and concrete resources: /llms.txt, Lighthouse 13.5 /.well-known/ai-catalog.json (ARD 1.0), plus HTML head and robots.txt snippets. The sibling differentiation is explicit (extract_byte0_markdown for scraping, audit_ai_readiness as the upstream detector).

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?

States exactly when to use it ('remediate missing discovery manifests identified by audit_ai_readiness') and when not to ('general web scraping (use extract_byte0_markdown instead)'). Both the trigger condition and the alternative tool are named, leaving nothing to inference.

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 already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new operational context: it is a static benchmark lookup requiring no API key, so no auth or rate-limit surprises. It stops short of describing result shape or pagination, but with annotations carrying the safety burden this is a solid addition.

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?

Front-loaded with the retrieval purpose, followed by usage and exclusion guidance, so an agent scanning the first clause gets the gist. The long parenthetical of measured metrics is dense but earned, since it explains what the benchmark actually contains. Slightly heavy, but every clause carries 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?

With no output schema, the description does useful work by enumerating the measurable fields (token weight, truncation cutoff, price omission, /llms.txt adoption, Lighthouse ARD), which tells the agent what comes back. It does not describe response structure or how the 50-site summary is organized, leaving a small gap for a data-retrieval tool.

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?

Single optional parameter with 100% schema description coverage; the schema already explains that omitting 'domain' returns the full 50-site summary, so baseline 3 applies. The description only loosely reinforces this by referencing peer comparison, adding no syntax, format, or canonical-domain details beyond the schema.

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 (retrieves) and resource (empirical benchmark telemetry from the 2026 50-Site SaaS & E-Commerce AI Truncation Study) and enumerates the measured dimensions, so an agent knows exactly what data lives behind it. It also distinguishes itself from siblings by name (audit_ai_readiness) and scope (study data vs. live scan).

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?

Explicit when-to-use ('comparing a site against industry peers', 'research questions about the Static /llms.txt Paradox') and explicit when-not-to-use ('Do not use this tool to run a live scan on an arbitrary unbenchmarked URL'), with the correct alternative named. This is the full when/when-not/alternative pattern.

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