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

Annotations already declare non-destructive, idempotent, non-read-only, so the bar is lower; the description still adds real context by warning that running work may incur provider cost and that cancellation doesn't guarantee refund or rollback. That is exactly the side-effect information the annotations cannot express.

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 short sentences with zero filler, with the primary action stated first and the caveat second. Every sentence earns its place.

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?

The description covers the crucial caveat for a mutation tool with no output schema, but leaves the parameters and the practical workflow (check status, what state the job ends in) undocumented. Adequate but with clear gaps.

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 description coverage is 0% for two parameters, and the description never mentions jobId or workspace, including the UUID pattern or why a workspace scope exists. The agent gets no semantic help beyond the bare 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 queued job') and narrows the scope to queued work, which distinguishes it from read_preparation_job and read_preparation_actions. It does not name any sibling explicitly, so differentiation relies on the agent inferring the queued-vs-running distinction.

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 word 'queued' implies the applicable state, but nothing tells the agent what to do when the job is already running, nor points to read_preparation_job to check status first. Usage is inferable rather than stated.

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