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

Annotations already declare destructiveHint=false and idempotentHint=true, but the description adds genuinely useful behavioral context beyond them: the underlying draft survives in the Drafts folder and content is not lost. That directly informs an agent's risk assessment before cancelling. It stops short of 5 because edge behavior (invalid or already-executed scheduleId) is not covered.

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?

Two sentences, zero waste, with the action and identifier front-loaded and the consequence ('content is not lost') placed immediately after as reassurance. Nothing could be cut without losing information.

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 two-parameter mutation with full annotation coverage and an output schema, the description covers the essential concerns: what is cancelled, how it is identified, and that it is non-destructive. The only real gap is not pointing at list_scheduled_emails as the source of scheduleId.

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?

With 50% schema coverage, the schema already documents accountId, but scheduleId has no description there and the description only repeats that it identifies the schedule — it does not say where to obtain it or what happens with a stale value. Baseline 3 is appropriate: it names the key parameter but adds no semantics beyond 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?

States a specific verb and resource ('Cancel a pending scheduled send') plus the identifying argument ('by its scheduleId'), so the agent knows exactly what the tool does. It does not explicitly name or distinguish itself from related siblings like list_scheduled_emails or get_delivery_operation, which keeps it short of a 5.

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?

Usage is implied by the object of the verb: you call it to cancel a pending scheduled send. There is no explicit guidance on prerequisites (e.g., obtaining the scheduleId from list_scheduled_emails) or on what to do instead when the send is already in flight, so the agent must infer the workflow.

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