reject_draft

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

With no annotations, the description carries full burden and delivers: it notes the owner-only restriction, that rejection is undoable via the web UI undo journal for ~10 seconds, that the reason/comment surface in the employee's view, and that the draft must be pending. These are concrete behavioral details that help an agent understand side effects and constraints.

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 compact and front-loaded: it starts with the primary action and outcome, then gives usage triggers, parameter guidance, and behavioral caveats in a logical order. Every sentence adds value; no fluff or repetition.

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?

Given the tool's moderate complexity (3 params, no annotations, no output schema), the description covers all essential aspects: purpose, when to use, parameter semantics, status precondition, permission (owner-only), and undo behavior. It is thorough enough for an agent to invoke the tool correctly without additional context.

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?

Although schema coverage is 100%, the description adds meaning beyond the schema: it explains that the reason and comment both surface in the employee's view, and that if none of the five reason categories fit, one should set reason to null and use the comment. This clarifies parameter usage in a way the raw schema does not.

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 clearly states the tool's action: 'Reject a pending draft so the submitter knows it won't publish.' It uses a specific verb ('reject') and resource ('draft'), and distinguishes itself from sibling approve tools by focusing on rejection. The phrase 'so the submitter knows it won't publish' adds outcome clarity.

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 description provides explicit usage triggers: 'Use when the user says "reject this", "this one's no good", or describes a problem with a draft.' It also clarifies when to use the optional reason categories versus null/comment, and states the draft must be in 'pending' status. This is strong guidance beyond generic 'when to use'.

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