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

Annotations already signal a safe, read-only, idempotent operation; the description adds valuable behavioral detail: no page content is fetched, the result is a flat array of URL strings rather than objects, and it returns `response_time`/`request_id`. It also gives a measured latency of about 1.5 seconds. It does not discuss external-domain inclusion in prose, though the schema covers this.

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 front-loaded with the core purpose inclue first sentence, then covers controls, return shape, performance, and sibling routing in compact sentences. Every sentence earns its place; there is no filler or repetition.

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 12-parameter tool with full schema coverageizing and an output schema, the description supplies the missing conceptual context: what the tool returns, how it behaves, and when to prefer it over its siblings. Nothing essential for correct selection or invocation is left out.

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 all 12 parameters. The description highlights the most consequential controls (`url`, `instructions`, and the regex path/domain filters) but adds little meaning beyond what the schema already states. That meets the baseline for high schema coverage without exceeding it.

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: 'List a site's URLs from a root `url`'. It clearly distinguishes itself from siblings by stating it does not fetch page content and by naming `post_tavily_extract` and `post_tavily_crawl` as the content-oriented alternatives.

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?

Usage context is explicit: use this tool to 'size a site before committing to a crawl', then use `post_tavily_extract` for targeted content. It also tells the agent that `post_tavily_crawl` is the right choice when content and shape are needed in one call, leaving no ambiguity.

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