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

Annotations only carry the safety profile (readOnly/no-destruct/no-open-world); the description adds the substantive behavior an agent cannot get elsewhere: accepted formats and resolutions (PNG, 1366x768 to 3840x2160), size/count limits (50 MB each, 10 at a time), that the picker delegates uploading to upload_screenshot, that it returns ids, and that id ordering matters for the next call.

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-loads the client-gating constraint, then limits, then the delegation/next-step chain. Every sentence carries load, though the routing and next-step instructions could be tightened into fewer clauses.

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?

An output schema exists, so return-value explanation is unnecessary; the description compensates by covering input constraints, the delegation path, and the downstream handoff to set_screenshots. Nothing needed to invoke this correctly is missing.

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?

Only one parameter (appId) and schema description coverage is 100%, so the schema already documents it fully ('The app id from list_apps'). The description adds no further semantics about appId, so this is the baseline 3 rather than a strength.

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 concrete verb and resource (shows a file picker for listing screenshots) and immediately scopes it to 'clients without a shell, like ChatGPT'. It is clearly differentiable from upload_screenshot (shell clients) and set_screenshots (which consumes the resulting ids).

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 when-to-use ('clients without a shell, like ChatGPT'), an explicit non-obvious exception ('even when the person attached the PNGs to a message'), and the alternative for other cases ("Clients with a shell use upload_screenshot's upload link instead"). The follow-on step (pass ids in order to set_screenshots) is spelled out.

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