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

Beyond the annotations it discloses the auth scope required (actions.write), a human-confirmation gate, what is preserved despite destructiveHint=true ('finding, evidence and score'), and precise conflict-resolution semantics for intent_saved_refresh_pending. That is substantial behavioral context an agent could not derive from the structured fields alone.

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?

Front-loaded with the action and scope, then prerequisites, then the preservation guarantee, then the conflict edge case. Every sentence adds decision-relevant information with no 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?

For a destructive, 4-required-param mutation with no output schema and zero schema descriptions, it covers confirmation, permissions, non-destruction guarantees, and one known conflict mode. It omits the relationship between auditRunId and findingId and other failure modes, but is largely sufficient to call correctly.

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 0%, so the description must carry the burden. It usefully ties 'urls' to 'the exact URLs displayed in an audit finding' and maps 'confirmedIntent' to explicit customer confirmation, but auditRunId, findingId, and the maxItems=4 URL cap are left entirely to the schema.

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 ('Acknowledge an intentional retrieval restriction') and scopes it to 'only the exact URLs displayed in an audit finding'. It does not name the sibling devtune_reconsider_retrieval_restriction, so the opposite operation must be inferred, but the action itself is unambiguous.

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?

Gives concrete preconditions ('Requires explicit customer confirmation and actions.write') and a hard prohibition ('Never infer customer intent'), plus explicit guidance on the intent_saved_refresh_pending conflict case ('do not repeat the call'). It stops short of naming when to use reconsider_retrieval_restriction instead.

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