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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds genuinely new behavior: locked reports truncate to the top three issues and check statuses while unlocked reports return every finding with fixes plus the written summary, and it discloses the 90-day retention window and absence of usage limits. This payload-shape and retention detail is exactly what an agent cannot infer from structured fields, especially with no output schema.

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 compact sentences, front-loaded with the core action, then id sourcing, then return shape, then retention and limits. No sentence is filler.

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 one required parameter, no output schema, and safety already covered by annotations, the description supplies the missing pieces an agent needs: where the id comes from, how response detail varies by lock state, and how long reports survive.

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% and the schema already says "8 characters," so the baseline is a 3; the description earns extra by explaining that the id is the last segment of a report URL, which tells the agent how to source the value. It stops short of saying whether a full URL is accepted as input.

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?

"Returns a previously run audit by its id" states a specific verb and resource, and the stored-report framing cleanly separates it from the sibling run-audit tools (audit_site, audit_product_page). The reader knows exactly what they get back without opening the 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?

The link-format hint (tools.roasexpert.com/r/<id> or /p/<id>) tells the agent where this tool applies in practice, and the locked/unlocked distinction sets expectations for the call. It never explicitly routes to unlock_report for locked reports or states what to do when an id is unknown, so context is clear but exclusions are absent.

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