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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuine behavioral context beyond that: failed and canceled tasks expose error_code and error_message, and their credits are refunded automatically — information an agent cannot infer from the schema or annotations.

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 sentences, front-loaded with what the tool returns, then the failure-case behavior. No filler or restated naming.

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?

No output schema exists, and the description compensates by naming the key return fields (status, URLs, cost_credits, error_code/error_message). For a simple single-id lookup this is nearly complete; only the origin of task_id and the polling-vs-wait distinction are left implicit.

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?

One required parameter (task_id) with 0% schema description coverage. The description only implies the identifier comes from a previously created task; it adds no format, source, or validity detail beyond what the schema shows. Baseline 3 given a single trivially-named parameter.

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 (Get) plus the resource (task) and enumerates the returned fields (status, output URLs, cost_credits). It also scopes to 'one of the authenticated user's tasks' and lists the task types, which separates it cleanly from the generate_* siblings and from list_* tools.

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?

Usage is implied (retrieve status for a known task_id) but there is no explicit guidance on when to call this versus wait_for_task, nor when to prefer it over polling. The presence of wait_for_task as a sibling makes the missing routing instruction a real gap.

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