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

Adds behavior the annotations cannot express: a finished request is billed on first read (a real cost consequence despite readOnlyHint=true), ungraded targets return a locked summary, and nothing is surfaced to the user until sightglass_show is called. These are precisely the non-obvious execution traits an agent needs.

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-loaded with the core action and mode selection before the caveats and the follow-up instruction. Dense but every sentence carries information; the only mild cost is the length of the billing/show-handoff clauses packed into one paragraph.

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?

With no output schema, the description does the work of describing returns: scores, findings and fixes, a locked summary for ungraded targets, and a resultId used for the show handoff. That covers the agent's decision needs; only the exact shape of the locked-vs-unlocked payload remains implicit.

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 baseline is 3, but the description adds relational meaning the schema does not: requestId is mutually exclusive in practice with a target while a grade runs, and adId/sitePageId select what dimension of the grade is returned. It stops short of explaining how workspaceId interacts with projectId beyond the schema's own note.

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 ('Read an X-ray') and then immediately disambiguates the two modes: polling a requestId vs reading a grade via adId/sitePageId. It is clearly separable from sightglass_xray (which starts a grade) and sightglass_show (which renders it), so an agent can route correctly without opening any 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 explicit conditional routing: pass requestId while a grade is running, pass adId or sitePageId to read an existing grade, and 'offer to run sightglass_xray' when a target is ungraded. It also prescribes the follow-up step ('call sightglass_show once with this call's resultId') and notes the show call does not re-search.

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