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

The description adds behavioral context beyond annotations: it mentions 'Effect: external-email,' the limitation that provider-accepted emails cannot be recalled, and retry behavior with idempotency key. Annotations already indicate destructiveHint and idempotentHint, but the description clarifies the idempotency usage for retries without contradicting the hint.

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 (4 sentences) and front-loads the main purpose. It includes relevant details (permissions, effect, retry, API reference) without excessive verbosity. The structure is logical and each sentence earns its place, though the API link could be considered extra.

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 description covers essential aspects for a cancellation tool: purpose, scope (not provider-accepted), retry mechanics, effect, permissions, and references. With an output schema present, it doesn't need to describe return values. It is adequately complete for the complexity, though it could mention error scenarios or prerequisites.

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 parameters are already well-documented. The description reiterates the idempotency key usage for retries but does not add significant new meaning beyond what the schema provides. It meets the baseline for high coverage without adding extra parameter insights.

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 purpose: 'Requests cancellation for delivery work that has not reached the provider.' It uses a specific verb (Requests cancellation) and resource (delivery work), and distinguishes it from other broadcast operations by noting provider-accepted emails cannot be recalled. This differentiates it from similar tools like broadcasts_unschedule.

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?

Provides clear context on when to use: cancellation is only possible before provider acceptance. Also gives retry guidance: 'Repeat the same request with the same idempotency key when the response is lost.' However, it does not explicitly name alternatives (e.g., broadcasts_unschedule) or state when not to use it, so it lacks explicit exclusions.

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