cancel_job

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

With no annotations, the description carries the full behavioral burden. It discloses one useful constraint (only queued/waiting jobs are cancellable) but says nothing about permissions required, whether cancellation is reversible, what happens to a running job, or how errors surface for an invalid state.

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?

A single front-loaded sentence stating the action and its constraint, with no filler. Nothing needs to be trimmed.

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 explained, and the tool is trivially simple with one required parameter. Still, as an unannotated mutation tool it should at minimum state the consequence of cancelling and the failure mode for non-queued jobs.

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?

The single parameter job_id has 0% schema description coverage, so the description is the only place semantics could be added, yet job_id is never mentioned. No format, provenance (e.g., obtain via get_job/list_jobs), or validity rules are given.

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+resource ('Cancel a job') plus a scope qualifier (queued or waiting for a GPU), which clearly separates it from siblings like get_job, list_jobs and gpu_status. It does not name a sibling explicitly, but the action is unambiguous.

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 'still queued or waiting for a GPU' gives an implicit applicability condition, so the agent can infer this is for not-yet-running jobs. However, there is no guidance on what happens if the job is already running, no idempotency note, and no alternatives suggested.

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