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

Annotations already declare idempotentHint and destructiveHint, and the description adds real context beyond that: retries are deduplicated by exact identity plus unchanged body, and the result is revision-bound with no read attestation or human acceptance. It does not explain why a 'report' carries destructiveHint=true (presumably revision consumption), leaving one annotation unexplained.

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 dense sentences, front-loaded with the payload and followed by disambiguation and return semantics; nothing is filler. The middle sentence is a somewhat run-on parameter list joined by semicolons, but it stays readable.

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?

No output schema exists, and the description does supply the return contract (revision-bound command result, no attestation or human acceptance) and the retry contract. For a nested 2-parameter mutation with 50% schema coverage, the remaining gap is the revision-matching requirement that baseRevision/purposeRevision imply.

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 50%; several fields (baseRevision, purposeRevision, snapshotId, itemRevision, summary, evidenceRefs) have no schema descriptions. The description names most of them and adds the meaningful 1-20 evidenceRefs bound and the clientId retry-identity rule, but it never explains the role of baseRevision/purposeRevision (optimistic concurrency) or snapshotId, so the coverage gap is only partly compensated.

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 ('Records') and the exact payload it captures (itemId, itemRevision, evidenceRefs, summary), and explicitly separates it from verification/decision-completion tools. It stops short of naming a sibling tool outright, so the agent must still infer the boundary with purpose_report_action_done and purpose_support_decision.

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 'for human Accept / Not yet' clause implies the report feeds a human review gate, and 'The report is not verification or completion' gives a useful negative distinction. However, there is no explicit 'use this when X, not when Y' statement or prerequisite list, so call-site selection is still partly inferred.

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