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

With annotations declaring destructiveHint=true and idempotentHint=true, the description still earns credit: it explains that only human acceptance supersedes the pending proposal, that retries are identified by exact identity and unchanged body, and that the result is revision-bound and carries no read attestation or acceptance. Those are real behavioral facts not in the annotations.

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?

Four dense sentences, front-loaded with purpose and ending with the return contract; no filler. It is terminology-heavy ('revision-bound command result', 'read attestation') but every clause carries information.

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 revision-guarded, idempotent mutation with a nested command object and no output schema, the definition covers retry identity and the return shape. It never says where baseRevision, purposeRevision or snapshotId come from, which is the main practical obstacle to calling it correctly, and gives no sibling routing.

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% and the description compensates by naming clientId, baseRevision, purposeRevision, snapshotId and by qualifying decisionId, messageNumber ('full retained') and decisionText ('exact complete') as identity-critical. That adds meaning beyond the schema, whose decisionId description is in fact a copy of the clientId text.

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 opens with a specific verb and resource: 'Creates a revised pending proposal from decisionId'. An agent can immediately tell this is an amendment of an existing pending decision rather than a new one. It never names the sibling it contrasts with (purpose_propose_decision / propose_decision), so it stops short of a 5.

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 only implied: the tool takes a decisionId plus revisions, so it is for amending a decision that already exists, and 'Only human acceptance supersedes the old pending proposal' hints at the lifecycle. There is no explicit when-to-use / when-not or a pointer to purpose_propose_decision for new decisions, leaving the agent to infer the boundary.

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