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

The description adds meaningful behavioral context beyond the annotations. It discloses that rejection excludes the complete from billing and reopens the slot, which is a key effect. It also notes the 15% cap, which is a critical operational limit. The idempotentHint=true annotation is consistent with the description (rejecting the same complete twice would have the same outcome), and the description does not contradict any annotation. The only minor gap is that it doesn't state what happens when the cap is reached, but that's an edge case.

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 a single, well-structured sentence that front-loads the action and immediate consequence, then adds the cap and instruction. Every clause earns its place: the purpose, the effect, the constraint, and the required reason. There is no fluff or redundant repetition of the tool name or title.

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 mutation with three documented required parameters and no output schema, the description covers the essential context: when to use, what happens, and a constraint. It lacks detail on error handling (e.g., what if the cap is exceeded) or exact behavior when called after close, but these are edge cases not typically required for a tool of this simplicity. Overall, the description is complete enough for an agent to invoke it correctly.

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?

The input schema already provides thorough descriptions for all three parameters (reason, survey_id, location_id) with full coverage (100%). The description adds little beyond the schema, except a reinforcement to provide a concrete reason. It does not introduce new syntax or format details. Since the schema carries the parameter semantics, a baseline score of 3 is appropriate, and the description does not compensate further.

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 action (reject a complete) and the resource (a 'complete', i.e., a survey response). It also specifies the timing ('before close') and the consequences (excluded from billing, slot reopens). This distinguishes it from other tools that operate on completes, such as list_completes, which lists them, or accept_workspace_invitation, which is unrelated. No other tool in the sibling list performs a rejection, so the purpose is 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?

The description gives explicit context for when to use this tool: before close, and for low-quality completes. It also provides a constraint (capped at 15% of the target) and a directive (give a concrete reason). It does not explicitly name alternatives or state when NOT to use it, but since there is no alternative rejection tool, the implicit guidance is sufficient. It could be improved by noting that this should only be used when a complete is truly invalid, not for routine edits.

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