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

Annotations already declare idempotent, non-destructive, closed-world behavior, and the description adds genuinely new context: results are 'retained' evidence, expired results raise an error rather than returning stale data, and the caller must preserve coverage/version/warning metadata. The only tension is that 'Retrieve' reads as a pure read while readOnlyHint=false, but that is a conservative default rather than an outright mutating claim. No auth or rate-limit detail is given.

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?

Three tight sentences with the core action front-loaded, followed by the failure mode and retention caveats. The final clause ('Preserve coverage, versions, warnings and potential-match review requirements') is slightly cryptic and reads more like an instruction to the consuming agent than a description of the tool, which slightly dilutes an otherwise efficient block.

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 an output schema present, the description does not need to enumerate return fields, and it correctly focuses on scope, retention, and the expired-result error. For a single-parameter retrieval tool this is nearly sufficient, missing only guidance on behavior when the ID is invalid or the result is absent.

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?

There is a single parameter, and the schema fully specifies it as a UUID string with an explicit pattern and format, so the schema already carries the constraint burden (coverage 0% here reflects absent prose, not absent constraints). The description adds only the notion that the ID is a 'screening ID' identifying retained evidence, which is a modest clarification over the schema field name 'id'.

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 gives a specific verb and resource — 'Retrieve retained evidence by screening ID from the connected sandbox workspace' — which is unambiguous about what comes back and the lookup key. It implicitly separates itself from run_sandbox_screening by framing this as retrieval of an existing result rather than execution, though it never names the sibling outright.

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?

Usage is implied (fetch a result by ID after a screening has run), and one useful precondition is stated: 'An expired result is an error.' However, there is no explicit when-to-use guidance, no mention of how this relates to run_sandbox_screening or validate_screening_request, and no statement about what to do if the ID is unknown or the result was never created.

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