draft_delete

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

The annotations already declare readOnlyHint=false, openWorldHint=false and destructiveHint=false, and the description usefully reinforces the narrow blast radius by naming what survives (current edit, revision history, original media). That is genuine added context, but it stops short of saying whether the delete can be undone, what happens if draftId is unknown, or what the 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?

Two sentences, the destructive action front-loaded, followed immediately by the scope-limiting clause. No filler or redundant restatement of the tool name.

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 delete with no output schema, the definition covers effect scope but omits error behavior, idempotency, and where draftId comes from. Adequate to invoke, not quite complete for an agent that must decide safely whether to invoke it.

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?

Only projectDir carries a schema description (50% coverage); draftId is undocumented in both schema and description. The description adds nothing about draftId's expected form or provenance, so it fails to compensate for the coverage gap, though with just two parameters and one documented the baseline holds.

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 ("Delete") and a bounded resource ("one saved proposal"), which separates it from draft_list/draft_inspect/draft_apply. The only wobble is the terminology shift from "draft" in the tool name to "proposal" in the description, which leaves a small ambiguity about whether they are the same object.

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?

There is no guidance on when to delete versus archive or re-stage, no prerequisite that the draftId must come from draft_list or draft_inspect, and no statement about whether the deletion is reversible. The agent is told what the tool does but not when it is the right choice.

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