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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, and the description adds real content beyond that: it will not return body text, it will not return write hashes, and it does report section size, share of max_chars, template sections, and missing sections. The gap is that result_offset implies paging, and nothing in the description says results are paginated or how truncation is signaled.

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, front-loaded with what the tool returns before the negative constraints and the alternative. Every clause carries distinct information: output contents, the no-text constraint, the no-hashes constraint, and the sibling that supplies hashes.

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 small read tool with no output schema, the description covers return contents unusually well, but it leaves the identifier parameters and the result_offset paging parameter unexplained, which matters for actually invoking the tool on a large outline. Adequate, with a clear parameter-documentation 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 description coverage is 0%, so the description carries the full burden for three parameters, yet it never mentions project_id, document_id, or result_offset by name or meaning. Only an implicit notion of "a document" is conveyed, and paging via result_offset is entirely undocumented, so it fails to compensate for the empty schema 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?

"List the headings of a document with their paths and sizes (never the text)" gives a specific verb, resource, and output shape, and the parenthetical rules out the most likely misreading. It also names the sibling it is not (read_document) and what that sibling uniquely provides (hashes), so the two are distinguishable without opening a schema.

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?

"Use it to see where a change fits" states the intended situation, and the sentence about hashes coming with read_document explicitly routes the agent elsewhere for write preparation. What's missing is any guidance on when to prefer search_documents or read_document for plain reading, so the exclusions are only partially covered.

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