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

Annotations already declare destructiveHint=true and idempotentHint=true, so the deletion risk is covered structurally. The description adds real value on top: it discloses the refusal behavior when confirm is false and the eligibility constraint that only unpublished, unscheduled drafts qualify. Return/shape details are not covered, keeping it from a 5.

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, front-loaded with the operation and its scope, then the confirmation gate, then the exclusion. Every sentence carries distinct information with no filler.

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 two-parameter destructive tool with no output schema, the description covers eligibility, permanence, and the confirmation precondition — enough to call it safely. It stops short of explaining what happens to the draft afterward or error behavior in more detail, so not a full 5.

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 100% and both parameters (id, confirm) are already documented in the schema, including where the id comes from and that confirm must be true. The description restates the confirm requirement in prose but adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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States a specific verb and resource ('Permanently deletes an unpublished draft') with an explicit eligibility scope ('is_draft, not scheduled, not sent'). It also carves out what it does not touch ('Scheduled and published posts cannot be deleted'), which distinguishes it from siblings like unschedule_post and save_draft.

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 exclusions ('scheduled and published posts cannot be deleted') give clear guidance on when this tool is not applicable and must be replaced by a sibling. However, it does not name which alternative to use instead (e.g., unschedule_post), leaving that inference to the agent.

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