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

Annotations already declare destructive=true, idempotent=true and readOnly=false, yet the description still adds substantive behavior: a rate limit, the fact that new versions invalidate prior readiness, and that peer acknowledgment is not acceptance or closure. It also clarifies the return ('revision-bound command result without read attestation or human acceptance'), which goes beyond the structured fields. It does not explain what a destructive overwrite actually replaces or what happens on a revision conflict.

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?

The most important facts — what is recorded, the rate cap, the invalidation rule — are front-loaded, and every sentence carries information. It is dense and jargon-heavy but not padded; the parameter enumeration sentence is the weakest, since it partly restates the schema.

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, nested-command tool with no output schema, the description covers eligibility, rate limits, retry identity, invalidation semantics and the shape of the response. The main remaining gap is conflict/error behavior when baseRevision or purposeRevision is stale, which an agent would want before calling.

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 only 50%, and the two documented fields are partly unreliable — recipientId's description is a verbatim copy of clientId's retry-UUID text. The description compensates by naming title, recipientId, resultRefs, blockers, clientId, baseRevision, purposeRevision and snapshotId and by explaining that 'exact identity and body identify retries', but it never distinguishes baseRevision from purposeRevision or explains snapshotId.

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 gives a concrete verb and resource ('Records a draft title, recipientId, exact versioned resultRefs and optional free-text blockers') and identifies the eligible actor (current manager or claiming agent). It does not name any sibling tool such as purpose_report_criterion_met or confirm_acceptance to disambiguate, 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?

It states who may invoke it ('from the current manager or claiming agent') and a hard operating limit ('ten changes per room per hour'), which is real usage context. It never names an alternative tool or an explicit when-not-to-use case, so it is clear context without exclusions.

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