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

Goes well beyond the readOnly/idempotent annotations by disclosing billing ('a finished request is billed when first read'), workspace-level unlocking ('as far as the workspace has unlocked it'), locked-grade behavior for ungraded targets, and that output is data-only with no user-visible effect. These are exactly the non-obvious traits an agent needs before calling.

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, then proceeds through polling, reading, locked behavior, and the follow-up show call. Every sentence earns its place, though several parentheticals make it dense; structure is efficient but not maximally clean.

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 5-parameter read tool with no output schema, the description conveys what comes back (scores, findings, fixes, summary, resultId) and the states a caller will encounter. A complete field-by-field return picture is absent, but the actionable semantics are covered.

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 the per-parameter descriptions already carry the detail, making 3 the baseline. The description adds real routing semantics on top: which parameter selects polling vs reading the grade itself, a distinction the schema alone leaves implicit.

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 ('Read an X-ray') and immediately clarifies that this reads a grade, distinguishing it from sightglass_xray (which starts one) and sightglass_show (which displays one). The relationships to both siblings are named, so an agent can tell them apart 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?

Explicit routing: pass requestId to poll, pass adId or sitePageId to read a finished grade, offer sightglass_xray when nothing is graded. It even prescribes the downstream step ('call sightglass_show once with this call's resultId'), covering when-to-use, when-to-do-something-else, and the follow-up call.

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