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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds value beyond that by disclosing the return content (file URLs when finished) and the blocking/wait semantics of the call, which the annotations do not express.

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 short sentences, front-loaded with what is returned and followed by the one non-obvious invocation tip. No redundant restatement of the name or schema.

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 only two well-documented parameters and no output schema, the description does the necessary work by explaining what comes back and how waiting behaves. It could be slightly more complete about in-progress or failed states, but nothing critical is missing for correct invocation.

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 taskId's origin and waitSeconds' 0-30 bound are already documented in the schema. The description adds only the motivation for waitSeconds (avoid a polling loop), which is a small increment over the schema baseline of 3.

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 resource (a generation task) and outcome (status, then file URLs once finished), so an agent knows exactly what it retrieves. It does not explicitly contrast itself with siblings like list_generations, so it falls short of a 5.

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 a concrete usage rule: pass waitSeconds to block until completion rather than polling in a loop. That covers the main decision an agent faces here, though it offers no guidance on when to prefer list_generations or how to handle unknown/failed taskIds.

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