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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds the behavior that matters: the ~45 second blocking cap, the need to re-poll, and that videos take several minutes. It does not describe what a failed or errored run looks like in the response, which is the main remaining gap.

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?

The purpose and output come first, then id semantics, then the polling guidance — good front-loading. The final parenthetical about median render times is long and slightly redundant with the wait advice, but it still carries 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?

With no output schema, the description correctly takes on the return-value burden by naming the output URL and media types. It is nearly complete for a 2-parameter polling tool; only failure-state handling is 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?

Schema coverage is 100% so the baseline is 3, but the description adds real semantics the schema lacks: run_id accepts ids from ANY agent-media tool and resolves run id, skill run id, and job id interchangeably. The wait parameter's blocking behavior is reinforced beyond the schema's own wording.

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+resource ('Check a generation you already submitted') and the payoff ('get its output URL (video, image or audio)'). This is unambiguously distinct from the generate_* siblings, which create runs rather than inspect them.

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 conditional instructions: 'ALWAYS call this after submitting', 'Set wait:true to block', and 'if it is still running, just call again'. It even routes the agent to list_models `recent` to estimate render time, so the polling decision is grounded in another tool.

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