Injuries and health

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It excels by explaining non-obvious behaviors: old wounds are never deleted and thus old_wounds_only dwarves are not casualties; sleepers are excluded from unconscious because they carry a nonzero unconscious counter; care_needs is empty when no care is required; and it returns an error if no fort is active. These details go far beyond the schema and provide crucial edge-case understanding.

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?

The description is a single paragraph but is tightly packed with necessary information. It starts with the main purpose, then defines each category, explains edge cases, and ends with the error condition. Every sentence adds value and there is no redundant or filler content. It is verbose but highly efficient for the complexity it covers.

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?

Given the lack of output schema, the description must explain return values. It thoroughly explains the semantics of each field (wounded, old_wounds_only, patients, bedridden, unconscious, care_needs) and the error case, but it does not explicitly state the exact JSON structure (e.g., whether the fields are arrays of IDs or counts). This leaves a small gap, but the definitions strongly imply the format, so it is mostly complete. A 4 is appropriate.

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?

The tool has zero parameters, so the input schema is empty and schema_description_coverage is 100%. No parameter explanation is needed from the description. The baseline for 0 params is 4, and the description does not need to compensate for anything. It appropriately does not mention parameters, which is acceptable.

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 clearly states it provides 'The fort's medical picture' with a focus on CURRENT condition rather than history. It specifically defines the resource and content, distinguishing it from any other medical-related siblings by enumerating unique categories like wounded, old_wounds_only, patients, etc. This is a specific verb+resource with clear scope.

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 description provides clear context for when to use the tool: when you need the fort's current medical picture, with detailed definitions of what counts as wounded, patients, etc. It does not explicitly mention alternatives or exclusions, but the context is clear enough to infer the appropriate usage. A score of 4 is appropriate as it falls short of explicitly naming when not to use it or citing alternatives.

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