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

The description discloses key behaviors beyond the annotations: idempotency is explained concretely ('calling it again with the same sources returns the existing job (replayed: true)'), the credit model is clarified ('credits are only spent by unlock_job'), and the immediate return shape is described ('same shape as get_job plus replayed and next'). This adds significant context that annotations alone don't provide.

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?

The description is dense but every sentence earns its place: it covers cost, idempotency, the one-job-per-upload rule, auth requirements, return shape, and next steps. It's front-loaded with the core action and immediately gives the most important caveat (costs nothing). No filler or repetition of schema details.

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 tool with 3 params, no output schema, and rich annotations, the description covers everything an agent needs: prerequisites (prepare_upload), cost model, idempotency behavior, auth requirements, return shape, and polling instructions. The only minor gap is that it doesn't explicitly state error cases, but the description is complete enough for correct invocation.

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%, so the schema already documents all parameters. The description adds meaning by explaining the relationship between sources and outputs ('One set of uploads makes exactly one job') and the replayed behavior when calling with the same sources. It doesn't add per-parameter syntax details, but the schema is thorough, so the baseline 3 is exceeded by the added semantic context.

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?

The description states a specific verb ('Queue'), a resource ('an Odile Formats job'), and the source of inputs ('sources uploaded with prepare_upload's helper'). It clearly distinguishes this from siblings like unlock_job and get_job by explaining what this tool does (queue) versus what others do (unlock, poll).

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 description explicitly says when to use this tool (after prepare_upload, before unlock_job), what it costs (nothing), and what to do instead if you need different outputs (upload again with prepare_upload). It also tells the agent to poll get_job until ready, providing clear routing to the correct sibling.

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