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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, and the description goes further by explaining that partial cancellation is possible and that surviving emails appear in not_cancellable, plus the operational consequence of repeating the call. It does not discuss permissions or rate limits, so it stops short of fully independent behavioral coverage.

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?

Four short sentences, front-loaded with scope, followed by edge-case behavior, idempotency, and the confirmation guardrail. No filler or redundant restatement of the title.

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?

An output schema exists, so return values need not be spelled out, and the description still surfaces the not_cancellable field's meaning for the agent. For a single-parameter destructive tool this is nearly complete, with only permission/authorization context missing.

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% and the single batch_id parameter is already documented in the schema as 'batch_…'. The description adds no syntax, format, or validation meaning beyond that, so the baseline of 3 applies.

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 ('cancel') plus resource ('every email in a batch send') and a precise scope qualifier ('still scheduled'), which immediately separates it from the read-only get_batch sibling. An agent knows exactly what this tool does and what subset it touches.

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?

Gives clear conditions for use and non-use: only scheduled emails are cancelled, while queued or sent ones are untouched. It also adds a precondition ('Confirm with the user before cancelling'), though it never names an alternative tool or recovery path explicitly.

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