Authorize exact publisher action

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-redundant context: the record is a guarded grant with bounded meaning and 'Does not pay', which prevents an agent from treating success as publication. It does not disclose idempotency behavior (e.g. whether re-authorizing the same revision is rejected or duplicated), which matters given idempotentHint=false.

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?

Two dense sentences with no filler, and the precondition is front-loaded ahead of the semantic caveats. The semicolon-chained clause is packed but every element (authority, revision, digest, action, attestations, truthfulness) carries distinct meaning.

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 non-idempotent mutation with six required parameters and no output schema, the description covers preconditions and non-effects well but leaves gaps: no indication of what a successful grant returns, whether authorization can be superseded or re-issued for the same revision, or what failure looks like. An agent could call it correctly but not predict the result or recovery path.

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% across six required parameters, so the description carries the burden. It maps conceptually to revision, approved_digest, action and attestations, but adds no format, constraint or meaning beyond those nouns — notably it never explains that authorize_publisher must be true, nor what the attestation objects must contain. 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?

The description states a specific effect — 'Records a guarded grant' — scoped to an exact task revision, digest and submit/publish action, which is more precise than the title alone. It also carves out what it is not (proof of submission, approval or publication), helping separate it from get_publisher_task and create_publisher_task. It never names a sibling explicitly, so differentiation is inferential rather than stated.

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?

'Only use within existing explicit owner authority covering this exact task revision, digest, submit/publish action and truthful attestations; obtain missing authority first' gives a clear precondition and a required prior step. What is missing is routing guidance: no alternative is named for the case where authority does not yet exist, leaving the agent to guess which sibling establishes it.

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