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

Annotations already mark the tool as read-only, open-world, idempotent, and non-destructive, and the description adds substantial behavioral context: robots.txt respect, page cap, same-origin boundary, no JavaScript execution, no asset fetching, no recursive link following, and deduplicated findings. This goes well beyond the structured annotations.

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 short sentences carry distinct, non-redundant information: when to use, what it returns at most, what it avoids, and how to paginate. Every sentence contributes and the most important usage guidance 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?

Given the output schema is present and annotations cover side effects, the description is complete for safe invocation. It covers authorization, scope, limits, exclusions, and continuation, leaving no critical operational 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%, so the baseline is 3, but the description adds meaning by framing max_pages and page_offset as part of a sitemap-first bounded audit and by explaining when page_offset is needed. This gives the agent operational context beyond the individual parameter descriptions.

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 states a specific verb (audit), resource (public website), and scope (bounded, sitemap-first, at most 8 same-origin HTML pages). It also explicitly lists what it does not do, distinguishing it from sibling tools like check_broken_links and audit_public_webpage.

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?

It opens with an explicit 'Use this for' condition plus the authorization requirement. It clearly states what the tool will not do, signaling when a different tool is needed, and it instructs the agent to use page_offset to continue when more sitemap pages remain.

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