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

Annotations already mark destructiveHint as true Secret. The description adds important behavioral details: batching limit (100), per-item results, and partial success. However, it does not disclose the exact nature of per-item errors or how 'partial success' is reported (e.g., response structure, which item failed). Since no output schema exists, these details are left to the agent's inference, creating a significant gap for a destructive batch 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?

The description is a single sentence, concise and front-loaded with the core purpose and limits. It covers key points but could be slightly more structured to separate behavior from alternatives individually, though it is appropriately short.

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?

The tool is a batch destructive operation with no output schemaonics, so the description must fully explain the invocation context. It covers the batch size, optional reason, and partial success, but lacks details on error handling for per-item failures, which is critical for an agent to correctly interpret responses. Given the 'openWorldHint' and destructive nature, more completeness would be expected.

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 100%, so the schema describes the parameters (ids array with max 100, rejection_reason_id). The description adds the semantic that 'rejection_reason_id' is optional ('optionally with a reason') and clarifies the batch size limit, which helps beyond the schema. The lack of enum/description for rejection_reason_id's format is minor given the reference to 'hires_list_rejection_reasons' in the schema.

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 verb (reject), the resource (applications), and the batch scope (up to 100). It distinguishes itself from the single-reject sibling (hires_reject_application) by the batch aspect, so it is easily identifiable among siblings.

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 implies the batch use case (rejecting multiple applications) and mentions 'per-item results' and 'partial success allowed', which conveys behavior but does not explicitly contrast with the single reject alternative (hires_reject_application) or state when to choose one over the other. With the sibling named 'hires_reject_application', a more explicit routing would be helpful.

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