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

Beyond the readOnly/idempotent annotations, the description discloses the truncation limit (36000 characters), the text_chars_omitted counter, snapshot semantics ('as of fetched_at'), and two failure states with recovery paths (page_not_crawled with crawled_urls, no_site_crawl). That is exactly the behavioral context the annotations cannot carry.

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?

Purpose and payload are front-loaded in the first clause, followed by output contents, then constraints and error handling in a logical order. It is dense and slightly run-on, but essentially every sentence carries information an agent needs.

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?

There is no output schema, so the description compensates by describing the returned fields and the truncation counter, plus the two error codes and how to recover from them. For a four-parameter read tool this leaves nothing material unstated.

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: url and site_url_id are alternate addressing modes, and crawl_id overrides the default of the latest crawl. It reinforces rather than duplicates the schema's own 'pass this or url' note.

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 and resource: 'Read the words of one crawled page'. It enumerates exactly what is returned (title, meta description, h1-h3, body text, URL, page type, fetched_at), which clearly separates it from read_site_pages, and it refers to that sibling for obtaining site_url_id.

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 names concrete use cases ('quote, review or rewrite what a page actually says') and states a key constraint that governs selection: it reads the latest crawl or a given crawl_id, and never fetches the live page. There is no explicit 'do not use this for X' routing, so it falls short of a 5, but the context is clear.

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