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

Goes well beyond the destructiveHint=true annotation by disclosing retention windows (30 days, 7 for drafts), which actions are irreversible, the confirm gate, and account restrictions. It also describes the return payload, which no output schema provides.

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?

A single dense paragraph with zero filler: action semantics first, then safety protocol, then restrictions, then return shape. Every sentence carries information an agent needs.

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?

No output schema exists, yet the description supplies the return shape, and it covers the safety and permission context an agent needs before invoking a destructive tool. Nothing material is missing.

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 coverage is 100% and the enum already documents each action, so the baseline is 3; the description earns an extra point by tying confirm=true to the 'ask the user first' protocol, which is operational meaning the schema alone doesn't 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 specific verbs and resource: trash, restore, permanently delete the user's own recipes, and enumerates the five actions covered. Clearly distinguishable from siblings like update_recipe or restore_revision.

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 when-to-use routing: list_trash is read-only, delete vs delete_forever vs empty_trash spelled out, plus a mandatory prerequisite (ask the user first, then confirm=true) and an account-level restriction (blocked on read-only accounts except list_trash).

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