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

Although annotations already declare destructiveHint=true, the description adds critical nuance: it clearly states that sent notifications are unaffected, which is a key behavioral detail that prevents misinterpretation of destructive scope. This goes beyond the simple 'cancel scheduled notifications' title and provides valuable context about what is preserved.

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 conveys the core action (cancel scheduled emails), the scope (all scheduled for a candidate), and a key exception (sent ones unaffected). No filler or repetition; every part earns its place, and the important nuance is 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?

Given the tool has only one parameter and no output schema, the description sufficiently covers the action and its behavioral scope. It is complete enough for an agent to understand the tool's effectyahoo without additional context. However, it could briefly mention that only scheduled, not sent, notifications are affected, which it does. The lack of alternative tool guidance slightly reduces completeness, but for a simple cancel operation, it is adequate.

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 schema already provides full coverage (100%) for the single parameter `candidate_id` with its description 'Candidate id or alias'. The tool description adds no additional semantic meaning about the parameter, such as how the alias is resolved or any constraints. Since the schema carries the burden, a baseline of 3 would be expected, but the description fails to add even marginal context, so a score of 2 is warranted for lack of added value.

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 cancels all scheduled notification emails for a candidate, and explicitly notes that sent ones are unaffected, distinguishing its scope from related operations like deleting or updating individual notification messages. However, it does not explicitly differentiate from the sibling `hires_delete_notification_message`, though the description implies a bulk cancellation versus a single delete.

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 this tool (to cancel scheduled notifications for a candidate) but does not provide explicit guidance on when not to use it or alternatives. Given the sibling `hires_delete_notification_message`, the tool could benefit from noting that this is a bulk operation for all scheduled messages, not a per-message delete. The description is clear about the effect but lacks exclusion guidance.

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