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

Annotations only declare readOnlyHint and openWorldHint=false. The description adds meaningful behavior the annotations cannot convey: a hard privacy constraint ('Do not send the image, and leave out real names, emails, prices or customer data: structure only') and the return shape ('short report with the closest references (the best match's screenshot attached)').

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, front-loaded with the core action, then the procedural constraint, then the return value and next step. No sentence is filler; the 'structure only' warning is placed right where the agent needs it before filling fields.

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 10-param, no-output-schema tool the description covers purpose, the privacy-critical authoring procedure, the returned report contents, and the follow-up handoff to pickReference. Nothing an agent needs to invoke it 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?

Schema description coverage is 100%, so the baseline is 3 and the 10 field descriptions already carry the per-parameter meaning. The description adds the governing philosophy behind those fields — describe the structure in them, structure only, no PII — which clarifies how they should be filled beyond the raw schema text.

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 ('Find the real product screens closest to the user's own screen or flow and compare them') and names the exact comparison dimensions (step counts, plan counts, page sections). It is clearly distinguishable from siblings like search_screens or get_screen by its compare-the-user's-own-UI framing.

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 explicit ordering ('First look at the user's screenshot or running app yourself, then describe its structure in these fields') and a routing rule to a named sibling ('pass their ids to pickReference') for the chained workflow. The condition that selects the next tool is spelled out, not left to inference.

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