score_vehicle

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so repeating 'Read-only' earns little. The description does add genuine behavioral context beyond annotations: results are hints about where a metric falls outside the reference min-max, and references vary in size and purpose so a miss is not a defect verdict. It does not cover failure modes such as a missing or empty reference set.

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?

Four sentences, front-loaded with what is compared and against what, then result semantics, then the caveat. Minimal waste; the trailing 'Read-only.' duplicates the annotation rather than earning its place.

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 an output schema present, return values need not be explained, and 8 parameters are fully covered by the schema. The description supplies the comparison model (min-max of same-kind references) and interpretation guidance. Slightly incomplete on how kind is resolved and what happens with an empty or mismatched reference set.

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 baseline is 3. The description adds organization beyond individual param docs by framing the input as three alternative modes (saved vehicle by name, draft/stored design, or hull spec/preset) plus the shared reference set, which helps an agent assemble a valid combination. It still leaves the kind parameter's default-detection behavior and patch ordering to the schema.

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?

The description names a specific verb+resource: compare a saved vehicle, design, or hull spec against a reference set from study_references, with per-metric min-max checking. An agent can tell this is a benchmarking/scoring operation rather than a build or validate one. It does not explicitly distinguish itself from analyze_vehicle, analyze_hull, or preflight_vehicle, which are the nearest siblings.

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?

Usage is implied rather than stated: you compare against a set saved by study_references(save_as=...) to see where metrics fall relative to peers. The caution that 'a miss says where to look, not that the vehicle is broken' is helpful framing for interpreting results. However, there is no explicit when-to-use vs analyze_vehicle/preflight_vehicle guidance and no stated prerequisites (e.g., needing an existing reference set).

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