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

Annotations declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint all safe, and the description adds valuable context: 'Measured at about 9 seconds,' 'Billed 1 credit per discovered link,' and 'Returns success, a request id, and links[] with url and title — note these are objects with a title, unlike post_tavily_map which returns bare strings.' It goes beyond the annotations by quantifying latency and billing, and highlighting a critical data format difference. Not a 5 because it doesn't mention pagination or rate limiting, but strong for annotation coverage.

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 tightly written, with each sentence earning its place: what it does, key requirements, return format, timing, billing, and alternatives. It front-loads the core purpose and requirements. No fluff.

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 tool is simple (2 params, no nested objects) and has rich annotations plus a fully covered schema. The description covers usage context, output format, performance, and cost. It also compares with siblings to prevent misuse. For this complexity, nothing critical is missing.

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 the schema already documents both parameters. The description adds that both are required (redundant with schema) and that limit is a cost control ('cost control, not just a page control'), which provides insight beyond the schema's 'Maximum number of links to discover.' This is useful, but since schema covers semantics, 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?

The description clearly states the tool's purpose: 'List the URLs reachable from a starting page, without fetching any content.' This is specific and distinct from siblings like post_firecrawl_scrape (fetch content) and post_tavily_map (different format). The verb 'list' and resource 'URLs' are specific, and the exclusion of content fetching distinguishes it immediately.

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 explicitly says 'Use it to size a site before paying to crawl it, then fetch only what matters with post_firecrawl_scrape,' and contrasts with 'post_firecrawl_crawl' for content and structure in one pass. It also notes the cost control aspect. This gives clear guidance on when to use and when to prefer alternatives.

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