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

Annotations already declare write (readOnlyHint=false) and non-destructive/global scope, so the safety profile is partly covered. The description adds high-value context beyond them: the operation SPENDS the user's coins, the mismatch-refusal behavior means nothing is spent on failure, and the polling next step. This is material economic and failure semantics that annotations do not convey.

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 tight sentences, front-loaded with purpose and immediately followed by the critical cost warning. No filler; every sentence carries actionable 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?

Covers purpose, prerequisite, cost/refusal behavior, and the polling follow-up, which is strong for a write tool with no output schema. It stops short of saying what start_run itself returns (e.g. a run id to feed get_run), leaving a minor gap an agent would have to infer.

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 baseline is 3. The description still adds meaning by binding expected_total and version to estimate_run's output and explaining the consequence of a stale value (run refused, nothing spent), which gives these parameters semantic weight beyond their terse schema descriptions.

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 ('Start rendering a canvas') and situates it precisely in the workflow between estimate_run (which supplies version/expected_total) and get_run (which is polled). An agent can distinguish it from the sibling estimate/get tools 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?

Explicitly names the prerequisite sibling (estimate_run) and the follow-up sibling (get_run), and gives the condition that governs use: pass the estimate's values exactly or the run is refused. The routing to alternatives is concrete rather than implied.

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