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

The description adds meaningful operational detail beyond the annotations: it never starts anything, consumes no credits, can wait for a running task, and is restricted to the caller's own generations. These points align with readOnlyHint, idempotentHint, and destructiveHint=false, and enrich what the agent knows about side effects.

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-load the core action and resource, then add the key caveats (no cost, no side effects, waiting behavior, id provenance) without redundancy. Every sentence carries distinct useful 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?

For a single-parameter read/idempotent tool with rich annotations, the description covers the essential behavior: what it returns, when it waits, where the task id comes from, and that it is free and non-starting. No output schema is present, but this level of detail is sufficient for an agent to select and invoke the tool correctly.

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?

The schema already covers task_id fully, but the description adds value by specifying that task ids come from generation replies or list_generations and explaining how the task_id relates to finished versus running generations. This helps the agent select the correct value beyond the schema's simple field description.

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 opens with a specific verb ('Return') and resource ('one of the caller's own image or video generations by task id'), which is far more informative than the title. It distinguishes itself from generation tools by explicitly stating it never starts a new generation and from list_generations by targeting a single task id.

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 clearly indicates when to call it: when you already have a task id and need the finished generation, or when a generation is still running and should be awaited. It also tells the agent where task ids come from, though it does not explicitly name sibling alternatives or say when not to use them.

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