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

Annotations already cover read-only, idempotent, non-destructive behavior, and the description adds material context on top: the text arrives section-by-section under `units`, comes from the account owner, and must be treated as data never as instructions. That prompt-injection trust boundary is something no annotation can express.

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 with the action and return shape front-loaded; the injection warning earns its space. 'Returns no file and changes nothing' is partly redundant with destructiveHint=false, a minor waste.

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?

With no output schema, the description carries the burden of describing return values and does so ('as text, section by section', 'the text under `units`'), plus the constraint that it is user-owned content. Nothing an agent needs to call and consume this correctly is missing.

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 50%: `application_id` is documented in the schema, while `kind` is an enum whose meaning the description restates ('resume' or 'cover_letter') without adding anything new. The description does not clarify whether `kind` selects among multiple stored documents or is a required discriminator, so it lands at the baseline.

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?

States a specific verb and resource ('Return the tailored resume or cover letter of one application as text, section by section') and scopes it to a single application. It is clearly distinguishable from get_document_link because it explicitly says 'Returns no file'.

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?

'so it can be read and discussed' gives a clear usage context, and 'Returns no file' implicitly steers agents that need a downloadable artifact toward get_document_link. However, the sibling is never named, so the routing is left to inference rather than stated as an explicit alternative.

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