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

Adds real context beyond the annotations: entitlement tier, consent requirements, the idempotency-key obligation, and an exact-intent confirmation step, plus a read-before-write revision rule. The destructiveHint is declared but the description does not say what is overwritten, which keeps it just short of the top.

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 sentences, front-loaded with the action before prerequisites. The prerequisite sentence is dense but every clause is load-bearing; nothing is padded.

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?

Output schema exists so return values need no explanation, and preconditions are well covered. But for a destructive write with four undocumented parameters, the description leaves the payload contract (how exception_notes keys map to exceptions) and the consequences of omitting exceptions unspecified.

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 0%, so the description carries the burden. It explains the idempotency_key and hints at expected_version via 'use its current revision', but never documents project_id, close_id, or the shape of the exception_notes map (which exception identifiers are valid keys). That is partial compensation only.

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: record explanations for evidence exceptions in the current close revision. That clearly distinguishes it from siblings like refresh_evidence and room_review. It stops short of naming an alternative explicitly, so it is clear but not sibling-routing.

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 (Startup tier or higher, read and write consent, idempotency key, exact-intent confirmation) and a workflow directive to read current state and pass its revision when updating. It does not say when to prefer this over refresh_evidence, so it is clear context without explicit alternatives.

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