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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds meaningful behavior beyond that: the method (NOAA position, homography, Monte Carlo) and the three-valued verdict vocabulary with the caveat that results are assumption-dependent and not an authenticity judgment. A note on seed-driven reproducibility vs. the idempotentHint would have completed it.

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?

Two tight sentences, front-loaded with the action and its inputs, then the return contract and boundary. Dense but no filler; a typo ('intestable') and heavy clause packing are the only minor costs.

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-parameter, nested-object tool with no output schema, the description usefully declares the return values, which is what the missing output schema would otherwise supply. But it leaves most parameters undocumented and gives no guidance on coordinate formats, sampling/seed semantics, or how control-point count affects reliability, so the definition is only partially complete.

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% across 10 parameters, including nested structures, so the description carries the full explanatory burden — and it only alludes to control points (4–16) and the shadow geometry. Key inputs such as pixel_sigma, samples, seed, time_sigma_minutes, second_shadow, and the px/world coordinate convention go entirely unexplained in both places.

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 ('Check solar-shadow consistency') and names the exact inputs it consumes: NOAA solar position, a ground-plane homography from 4–16 control points, and Monte Carlo uncertainty. It even specifies the categorical outputs and the scope boundary, so an agent can distinguish it from siblings like check_shadow_track 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?

It clearly frames when the tool applies (image measurements in hand) and explicitly excludes one use case ('never an image-authenticity verdict'), which is valuable negative guidance. It does not, however, route the agent to or away from specific sibling tools such as check_shadow_track, so sibling selection is left to inference.

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