Reject a draft

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

Annotations already declare destructiveHint=true, but the description adds meaningful context: the irreversible nature ('never be posted'), that the optional reason is stored for later retrieval, and a safety note about being safe for a draft-only agent token. No contradiction with annotations.

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?

The description is three sentences, each adding distinct value: action/effect, reason storage, and capability/security context. No wasted words, and key details are front-loaded.

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 simple rejection tool with two parameters and no output schema, the description covers the action, outcome, optional input meaning, and security context. It doesn't detail errors or idempotency, but annotations and the simple domain make it sufficiently complete.

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 0% in the description. The description gives semantic meaning to the 'reason' parameter (stored for the submitting engine to read back), but 'draft_id' is left to the schema with no added explanation. It partially compensates for the lack of schema descriptions.

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?

The description uses a specific verb ('Reject') and resource ('pending or approved draft') and clearly states the effect ('so it can never be posted'). It distinguishes itself from siblings like approve_draft by focusing on rejection and permanent non-posting.

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?

It implies when to use (for pending or approved drafts that should never be posted) and mentions the reason is read back via list_drafts, giving context. It doesn't explicitly exclude alternatives, but the purpose is clear enough to guide selection among sibling draft-management tools.

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