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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the description doesn't need to re-establish that this is a destructive write. It does add real value by disclosing scope: ALL running runs are cancelled, not a single run. It does not state whether this is reversible, whether it errors when the contact has no runs, or how a `reason` is surfaced.

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?

One sentence, front-loaded with the action and scope, with the example trailing as supporting detail. No padding or repetition 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?

For a 4-parameter destructive action with no output schema, the definition covers action, scope, and contact-identification, which is most of what an agent needs. The remaining gaps (idempotency of repeated calls, behavior on contact-not-in-automation, precedence of email vs contact_id) are secondary but real for a destructive tool.

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% (id, email, contact_id documented), so the baseline is 3. The description adds the 'by contact_id or email' selector hint, but leaves the requiredness/mutual exclusivity of those two ambiguous and says nothing about the undocumented `reason` parameter or which identifier wins if both are supplied.

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 scope ('every running run of this automation for one contact'), which is meaningfully distinct from cancel-automation-run and stop-automation. It does not explicitly name those siblings, so the agent must infer the distinction, but the scoping is precise enough to differentiate.

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 embedded example ('when they bought and must leave a sales sequence') gives a concrete triggering scenario, which is genuine guidance. However, it never states when to prefer cancel-automation-run (single run) or stop-automation (whole automation) instead, and adjacent sibling names invite confusion for a destructive operation.

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