Record what you did about a finding

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

Annotations give the safety profile (not read-only, idempotent, non-destructive), and the description goes well beyond them: it states the side effect of 'ignored' (silences a finding), the rollback semantics of 'open', the hard restriction that 'verified' is unreachable here, and that no credit is consumed. That is exactly the extra context annotations cannot carry.

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, front-loaded with intent, then the status semantics, then the exclusion and the cost detail. Every clause conveys a distinct operational fact with no padding.

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 4-parameter mutation tool with no output schema, the description covers the status lifecycle, the reason requirement, and the alternative path for verification. It is slightly silent on what a successful call returns or how 'ignored_until' interacts with undo, though the schema covers the latter.

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 100% and the schema already documents status values, the conditional reason requirement, and finding_id provenance, so the description is largely restating them. It adds only the mild clarification that 'open' undoes either prior state, which the schema also implies. Baseline 3 is appropriate.

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 frames the operation functionally ('Remember a decision so a later session does not redo it') and enumerates the three status values it can set, which makes the resource (a finding's status) inferable but never states it directly as 'update a finding.' It does cleanly separate itself from verify_findings, so an agent can route correctly.

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 explicit per-value guidance: 'fixed_pending' for changes not yet deployed, 'ignored' to silence, 'open' to undo, plus the exclusion 'You cannot set verified: that is earned by calling verify_findings.' The cost note ('Free: does not use a credit') further arms the agent's decision between this and sibling tools.

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