clear_ideas

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

With no annotations, the description carries the burden and does well: it discloses that the operation is destructive, that it defaults to a non-destructive preview, and that the final call must follow user approval. It stops short of stating whether deletion is permanent or undoable and whether non-'done' ideas in a project scope are affected.

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 short sentences, each carrying distinct information: what is deleted, the default dry-run behavior, and the required confirm flow. The safety-critical gate is front-loaded ahead of any caveats.

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 2-parameter destructive tool with no output schema, the description covers the action, scope, and safety protocol adequately. The remaining gap is what the preview actually returns (count of ideas, list of names), which matters for the show-to-user step.

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?

Scope's accepted values repeat the schema text, but the description adds real meaning for the undocumented 'confirm' parameter — it defines the preview/commit gate and the approval condition, which the schema's bare boolean does not convey.

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 and resource — 'Delete many ideas' — with the bulk nature ('many') explicitly distinguishing it from the sibling delete_idea. The scope values are enumerated inline, so an agent knows exactly what population the tool acts on.

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 an explicit operating procedure: call without confirm to preview, show that preview to the user, then re-call with confirm=true only after approval. This is when-to-use, when-not-to-use, and the required human-in-the-loop ordering, all in the description.

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