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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the description's safety burden is low. It adds valuable context by labeling the operation as 'inexpensive' and framing it as a discovery step, which helps agents anticipate performance and purpose. However, it doesn't disclose potential rate limits or response format specifics, though annotations cover the main safety profile.

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 with zero filler. The first sentence immediately states the operation and purpose, and the second delivers the workflow guidance. Every word earns its place, and the most critical information (purpose and usage) is front-loaded.

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 2-parameter tool with clear annotations and no output schema, the description fully covers what an agent needs: what it does, when to use it (before crawl_site, before read_page), and why it's preferable (inexpensive). The implied output (a list of URLs) is sufficient for this simple discovery tool, and the workflow guidance makes it self-contained.

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%, with both 'url' and 'limit' clearly described in the schema (absolute URL, max 500 cap). The description adds no additional parameter-level meaning beyond the schema, so the baseline of 3 is appropriate; it doesn't need to compensate for schema gaps.

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 ('List a site's URLs') with a specific resource and purpose ('so an agent can select pages before reading them'). It explicitly differentiates from siblings by naming crawl_site as the heavier alternative and read_page for after mapping, making the tool's role 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?

Provides explicit when-to-use guidance: 'Prefer this inexpensive discovery step before crawl_site. Map first, then call read_page for selected URLs unless content from many pages is required.' This states the recommended workflow and explicitly contrasts with crawl_site (for many pages) and read_page (for selected URLs), leaving no ambiguity about decision-making.

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