kill_draft

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

With no annotations provided, the description carries the full burden. It signals destruction ("Kill") and that the seed survives, but says nothing about reversibility, whether the draft's content/history is lost, required permissions, or what happens on a nonexistent draft — all critical for a delete operation.

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 short sentence with the action and scope front-loaded and zero filler. It is terse to the point of under-specification, but nothing is wasted.

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 destructive mutation tool with no annotations, no output schema, and undocumented parameters needs substantially more disclosure than one sentence provides. An agent cannot determine safety, idempotency, or the role of `comment` from this definition.

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 0% across three parameters, so the description must compensate. It only implies seed_id and channel ("channel draft", "seed"), and never addresses the optional `comment` parameter or the meaning of the channel enum values.

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+resource ("Kill a channel draft") and adds a scoping clarification that the underlying seed is not destroyed, which implicitly separates it from kill_seed. The verb "kill" is jargon for delete, but the object and scope are unambiguous.

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?

No when-to-use guidance and no named alternative among siblings such as approve_draft, request_revision, or kill_seed. The parenthetical hint that the seed can remain is the only routing signal, and it is indirect rather than an explicit selection rule.

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