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

Annotations already carry the full safety profile (readOnly, idempotent, non-destructive, closed-world), so the description is free to add substance, and it does: the specific phenomena it evaluates and the three possible verdicts it returns. It stops short of explaining what each verdict means or how tolerance affects the outcome.

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 comparison and ending with the return vocabulary; no filler. Minor friction from the non-standard verdict spellings ('contredit', 'intestable') that force the reader to interpret rather than recognize.

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 and 0% schema coverage, the description is the only source of meaning, and it delivers the return-value vocabulary but not their semantics. Combined with the undocumented tolerance parameter, an agent has enough to call the tool but not enough to interpret or tune it.

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 0%, so the description must carry the parameter burden. 'Measured minute/azimuth pairs' partially documents the samples array, but date_utc, latitude, longitude, and especially the tolerance_deg threshold are left completely unexplained, leaving four of five parameters to be reverse-engineered.

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 ('compare measured shadow azimuths over time with the expected solar ephemeris') and enumerates the checks performed (slope, time-lapse speed, rotation direction, residuals). It is concrete enough to act on, but it never names or differentiates itself from the plausible siblings check_ephemeris and verify_shadows.

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?

The clause 'Inputs are measured minute/azimuth pairs, not video files' is a useful precondition on the expected data source. However, it gives no explicit when-to-use guidance relative to check_ephemeris or verify_shadows, so selection among the shadow/ephemeris siblings remains inferred.

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