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

Annotations already declare write/open-world/non-idempotent/non-destructive, so the bar is lower, but the description adds real value the annotations don't: an API-key auth gate and a human claim-and-pay step before the job executes. That cost/authorization constraint is exactly the kind of behavioral context the agent needs. It doesn't describe output or the subsequent approval step.

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 tight sentences with the core purpose front-loaded, followed by the preferred parameter and the hard prerequisite. The illustrative slug examples (duolingo, monzo, doordash) are compact and useful rather than padding. No wasted prose.

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?

For a 6-parameter write tool with nested objects and no output schema, the description covers purpose, routing, and the auth/payment gate. It omits the surrounding workflow – notably that a sibling approve_restyle exists, implying a review step – and gives no sense of what the call returns or how jobs are tracked. Adequate but with clear gaps.

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 only 33%, so the description is expected to compensate. It usefully disambiguates inspiration_slug (preferred over a free-text inspiration query) with concrete examples, but says nothing about source_app, inspiration_app, the screenshot URL arrays, or limit. Partial compensation for a low-coverage schema lands at 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 verb and resource: restyling the user's App Store screenshots against a directory inspiration set. The agent can distinguish it from create_localize and get_screenshots by the 'restyle to match inspiration' framing. It stops short of explicitly naming sibling alternatives, keeping it at 4 rather than 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 clear routing rule ('Prefer inspiration_slug from list_directory_apps') and a hard prerequisite (API key must be claimed and paid before generation runs). That tells the agent when the tool is usable and which parameter path to prefer. No explicit when-not or exclusion guidance is given.

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