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

Annotations declare readOnlyHint=true and the description is consistent with a non-mutating poll. It goes well beyond them: latency expectations ('usually takes 1–2 minutes'), the fact a single call may not be enough, the contents of the response (review link, per-screen headline, three directions), and the auth/signup caveat for the editor. That is exactly the behavioral context annotations cannot carry.

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?

Three tightly packed sentences ordered by what the agent needs first: what the call does and how it waits, then what comes back and what to do with it, then the retry instruction. No filler and no restatement of the 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?

There is no output schema, so the description carries the return-value burden and does so concretely (link, headline, three directions). Combined with the retry and signup notes, an agent has everything needed to invoke it and act on the result without further context.

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 schema already defines both parameters and the 0–50 bound, making 3 the baseline. The description adds real meaning by tying wait_seconds to the generation lifecycle and giving the 1–2 minute norm, which tells an agent the default 45s will often expire and a second call is expected rather than anomalous.

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?

Names a specific verb and resource ('Check on a screenshot set') and immediately adds the polling contract ('waiting up to wait_seconds for it to finish'). 'Step 3 of 3' positions it relative to the sibling workflow tools (prepare_screenshot_upload, generate_screenshot_set) so an agent can tell it is the terminal read step, not a generator.

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 actionable downstream instructions: share the returned link with the user, who then picks one of three directions; and explicitly says 'If it is still generating, call again.' That covers the retry loop clearly. It stops short of naming the sibling tool an agent must call first, so the prerequisite is only implied by the step numbering.

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