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

Annotations already cover the read-only/idempotent/non-destructive profile, and the description adds genuinely new behavioral facts: return shape is per-screen metadata, and images are capped at 4 with an explicit ~1-2k token cost each. That cost disclosure is exactly the kind of thing annotations cannot 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?

Three sentences, front-loaded with the search scope and examples, then returns, then the hand-off to get_screen. No filler and nothing buried.

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?

No output schema, so the description does step in with 'returns metadata per screen' plus the image-cost caveat, which is adequate for a search tool. What's missing is any mention of the filters object or plan-gated platforms, though the schema covers the latter.

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?

At 40% schema coverage the description has to carry weight, and it does for the two parameters that matter most: 'query' is illustrated with three contrasting example inputs (free text, 'Spotify', 'linear.app'), and 'includeImages' is given a quantity cap and token cost that the schema's bare boolean does not convey. The large nested 'filters' object (six sub-properties, one with no schema description) is never mentioned, which is the main gap.

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 ('Search individual UI screens') and immediately scopes what can be searched (description, app name, site) with three concrete example queries. It also explicitly contrasts with get_screen, so an agent can distinguish the discovery tool from the detail tool without opening a schema.

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 clear context for opting into images ('set includeImages to also get the top screens as images') and routes the agent to get_screen when full structure is needed. It does not address when to prefer search_screens_by_image or similar_screens, which are the closest siblings, so routing is clear but not exclusive.

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