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

Annotations already mark this as a non-read-only, non-idempotent write, so the description only needs added context — and it delivers: the record lands in an Approved state immediately, near-duplicates are refused and the conflicting item is named, and a wrong category is refused with the valid list. The auth requirement ('Fetch Hive staff only') is also disclosed. The only gap is that it never says what a successful call returns.

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?

Three tight sentences with the access restriction front-loaded, then the action and its outcome, then the content and duplication constraints. No sentence restates the title or the schema, and every clause carries information the agent would otherwise have to guess.

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 six-parameter non-idempotent write with no output schema, the description covers access, validity constraints, refusal behavior, and approval state. What remains unstated is the success payload (an identifier for the new idea?) and whether re-calling after a refusal is safe — minor, but not nothing for a non-idempotent mutation.

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 83% schema coverage the baseline is 3, and the description earns an extra point by clarifying that 'kind' defaults to workflow and by imposing a content rule on 'objective'/'notes' (must stay generic — no company names, URLs or emails) that the schema's maxLength constraints do not convey. 'Category' is only lightly touched — the description notes a wrong one is refused with a list, but does not explain how to choose among categories.

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 a specific verb ('Add') plus the resource ('a workflow (default) or agent template idea') and the resulting state ('straight to the library as Approved'), so the agent knows exactly what the call produces. The parenthetical '(kind)' ties the purpose to a named parameter, and the 'so the next batch builds it' clause explains the downstream effect, separating it from draft-oriented siblings.

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 clear preconditions: staff-only access, must be generic (no company names, URLs or emails), and must not duplicate a live template or open idea. These act as strong when-to-use/when-not-to-use filters. It stops short of naming an alternative path (e.g. saving a draft or building an idea directly) for cases that fail the duplicate check, leaving the fallback to inference.

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