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

Annotations already cover readOnly/idempotent/non-destructive, yet the description goes well beyond them: it discloses the run state machine, that failed runs persist whatever was saved in the same operations list, and that billing applies only when that list is non-empty. This is material behavior an agent cannot infer from the annotations or schema.

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?

Four tightly packed sentences, front-loaded with the poll loop, then outcomes, then the cost caveat. Every sentence carries an actionable instruction; nothing is redundant filler.

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 raw return values need no restating, and the description instead supplies the state-transition and billing semantics that the schema cannot express. For a polling tool with an open-world/polling risk, this is complete.

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 100%, so both runId and projectId are already documented (runId from data.runId in a design result, projectId from list_projects/create_project). The description reinforces that the run comes from a prior design call but adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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 opening sentence names the specific verb (poll) and resource (a design run) plus the exact states it applies to ('queued' or 'running'). It is trivially distinguishable from sibling tools like design, cancel_design_run, and screenshot without opening any schema.

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?

Explicit operating instructions: poll after design returns queued/running, wait a few seconds between polls, and branch on completed vs failed. It also gives a clear when-to-use rule ('Check it before resending the brief') and routes failures to the error message and optional error URL.

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