publication_review

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

With no annotations, the description carries the burden, and it does disclose the key non-publishing behavior plus the out-of-band approval flow. However, it does not state whether the tool is fully read-only, what side effects 'rebuild' might have, or any permission requirements.

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 sentences with no filler; the primary action is front-loaded and the critical 'Does not publish' constraint is its own sentence. Every part earns its place.

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 tool with 6 parameters, nested objects, no output schema, and no annotations, this description is too sparse. It does not describe the approval request return format, the meaning of metadata/destinations, or any prerequisites, leaving significant gaps for correct invocation.

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%, yet the description only hints that id relates to the draft and that metadata/rootDir/include contribute to 'package identity'. It does not explain exclude, destinations, or metadata semantics, so the agent cannot reliably map parameters to their roles.

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 names concrete actions ('rebuild the exact package identity', 'retrieve the draft', 'return the approval request') and explicitly states what it does not do ('Does not publish'). This clearly separates it from sibling publish_draft and makes its role obvious.

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 description gives clear context: this is for obtaining an out-of-band human approval request before publishing. The phrase 'Does not publish' acts as a when-not, though it does not explicitly name an alternative such as publish_draft.

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