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

Adds real side-effect detail beyond the annotations: reject archives the draft and the idea scout avoids it, and retry preserves the earlier attempt while resetting to Approved. However, the leading phrase 'Fetch Hive staff only' is ambiguous about whether it is a permission requirement or a resource scope, and no return values or failure modes are described. Annotations already cover readOnly/idempotent/destructive, so the added context is good but incomplete.

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?

Extremely dense but front-loaded with the scope caveat and then the three actions in a consistent order. The semicolon-chained single sentence is efficient, though 'Fetch Hive staff only' as an opener is cryptic and could mislead before the reader reaches the actual actions.

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?

A three-way state-transition mutation tool with no output schema needs to say what happens to the entity and what the caller gets back. Draft archival and attempt retention are covered, but return behavior and the staff/scope restriction remain unclear.

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?

With 50% schema coverage, the description is needed to compensate: it ties each enum value to a valid idea state, and explains that reason is consumed by reject and that retry goes back to Approved. The force parameter's meaning is only in the schema and idea_id is undocumented, which caps this at 4.

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 the exact resource (an idea) and the three concrete verbs (approve, reject, retry), and names the source/target states each verb operates on (Proposed/Rejected → approve, Failed/Needs a person/Ready for review → retry). Nothing is tautological, and the state vocabulary distinguishes it from generic sibling update tools.

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?

Gives explicit per-action conditions: approve only for Proposed or Rejected ideas, retry only for Failed/Needs a person/Ready for review ideas, reject when a reason is supplied. It does not name alternative tools or exclusions (e.g. when to use retry_run instead), which keeps it at 4 rather than 5.

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