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

Adds substantial non-obvious behavior beyond annotations: crawl scope (own site only, homepage start), robots.txt respected, page cap 25/default 15, the pass/warn/fail verdict structure, per-check evidence URL and fix, dated-study data as of 2026-10-01, and what is explicitly not fetched (claimed profiles, cover photos). Annotations (readOnly, openWorld, idempotent) cover safety; this gives the operational picture.

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 purpose statement, then usage triggers, then behavioral scope, then exclusions. Dense but each sentence carries signal. Slightly long, with a couple of clauses (Yext study date, cover photos) that could be trimmed, but nothing is filler.

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 a 2-param crawl tool with annotations covering safety and an output schema present, the description supplies everything an agent needs: trigger, scope, limits, verdict semantics, disclosure of what is not done, and what is returned. Complete without redundancy.

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 url and max_pages are already fully documented with types, bounds, and examples. The description confirms the same-site crawl constraint and 25/15 cap, which is marginal added value. Baseline 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?

Specific verb+resource: assesses local-business site readiness for AI-search citation, and lists exactly what it returns (pass/warn/fail for services, prices, FAQ, LocalBusiness schema, NAP). Clearly distinguished from siblings like audit_page/audit_site by the AI-search-readiness framing and named engines.

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 ('when the user asks if a local business site is ready to be named by AI search'), positive trigger phrases (ChatGPT, Gemini), and explicit exclusions: does not query AI engines, directories or review sites, does not measure rankings, and do not use for private addresses or contact collection.

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