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

Annotations only supply destructiveHint=true; the description adds genuinely new semantics by clarifying that the deletion is partial in effect — 'Runs it already cancelled stay cancelled' tells the agent this is not a rollback. It stops short of stating permission requirements or what the response contains, but the non-reversibility note is the key behavioral fact.

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?

Three short sentences, zero filler, and the effect of the call is front-loaded ahead of the semantics caveat and the endpoint. Every sentence carries distinct 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 one-parameter destructive delete with annotations covering the safety profile and no output schema, the description supplies purpose, partial-effect semantics, and the endpoint. It is nearly complete; only the source of cancellation_id and any auth expectations are unaddressed.

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 a single parameter and 100% schema description coverage, the schema already documents cancellation_id as 'The cancellation job's id.' The description adds nothing about format or where to obtain the id, so the baseline 3 applies rather than a higher score.

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 ('Delete a bulk-cancellation job') plus the effect ('so it stops cancelling further runs'), which lets an agent separate it from inngest_create_cancellation and inngest_list_cancellations without reading their schemas. The REST mapping reinforces exactly which resource is touched.

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 phrase 'so it stops cancelling further runs' implies the intent behind calling it, but the description never states the conditions for choosing this over siblings such as inngest_list_cancellations (to find an id) or a hypothetical resume/pause alternative. Usage is inferable, not explicit.

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