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

Annotations indicate destructiveHint=true, so the description does not need to restate that; it adds the optional 'suppress_notification' to skip the rejection emailaging the behavior. However, it does not disclose what happens on rejection: whether the application is permanently deleted, could be restored, or if any other side effects occur. The 'suppress_notification' is mentioned but its default behavior (notification sent by default) is not clarified, which might be important for an agent deciding whether to set it.

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, concise sentence that front-loads the primary action and two key options. It is efficient with wordshare no fluff. It could arguably be improved by splitting for clarity but is appropriately sized.

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 (4 params, no output schema), the description is sufficient to understand the primary action and parameters. However, it lacks detail on potential consequences beyond the email suppression, such as whether the rejection is permanent or reversible (though 'unreject_application' sibling implies reversibility). It also doesn't state the return value structure, which might be needed for an agent to process the result.

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 75%, meaning 3 out of 4 parameters have descriptions in the schema. The description does not add meaning beyond the schema for 'id' and 'include'; it mentions 'rejection_reason_id' as 'optionally with a reason' and 'suppress_notification' as 'without the rejection email', which aligns with schema descriptions. No additional parameter semantics are provided beyond what schema already offers.

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 'application', and the optional modifiers ('with a reason' and 'without the rejection email'). It distinguishes this from siblings like hires_advance_application and hires_unreject_application by its clear action of rejection, and the presence of 'suppress_notification' differentiates it from batch reject tools.

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 when to use it (when rejecting an application) but does not explicitly state when not to use it, such as when rejecting in bulk (use hires_batch_reject_applications) or when undoing a rejection (use hires_unreject_application). It gives no explicit comparison to siblings or conditions for choosing alternatives.

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