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

With annotations already declaring readOnly/idempotent/non-destructive, the description adds real behavioral context beyond them: lifecycle_status enumerations with semantics ('expired - took too long, credits auto-returned'), the legacy status field distinction, UTC/ISO 8601 timestamps, and the 25s long-poll cap. This is unusually informative for a read tool.

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?

Front-loaded with the return payload, then constraints, then sibling routing; nearly every clause carries information. Slightly dense with stacked parentheticals, which costs a little readability.

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, yet the description enumerates the return fields and explains status semantics, polling, and the cancel path, so an agent can call and interpret it. It omits error behavior (e.g. unknown or unauthorized id), a minor gap.

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 parameters are already documented, and the description's wait_seconds explanation largely restates the schema's long-poll text. Baseline 3 is correct; the added status vocabulary describes return fields, not inputs.

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 ('Returns one of your saved generations by id') and enumerates the returned fields (media URL, prompt, type, model, lifecycle_status, credits), so the agent knows exactly what it gets back. It also names the sibling cancel_generation for the stop-a-run case, making it distinguishable from the other generation 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?

Gives concrete selection guidance: use wait_seconds to long-poll rather than getting an immediate 'running', and use cancel_generation to stop a running job. It doesn't state when NOT to use this tool (e.g. versus get_task), but the polling and cancel routing cover the main decision points.

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