score_severity

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

No annotations are provided, so the description must fully disclose behavior. It does not mention side effects, permissions, rate limits, error handling, or whether it is read-only. The versioning comment is not about current behavior.

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 short (2 sentences), but the second sentence discusses future versions, which is noise and reduces conciseness. The first sentence is front-loaded and clear.

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 or annotations, the description should cover return values, error cases, and practical usage. It does not specify what the rubric looks like or how observations are used, leaving significant gaps for a tool with two required inputs.

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 0%, and the description only vaguely refers to 'observations' without explaining format or constraints. It adds little beyond the schema's property names, leaving the agent unclear about valid inputs.

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 states it returns a severity rubric for a dysfunction applied to observations, which gives a clear verb and resource. However, the mention of v0.1 and v0.2 adds unnecessary future context that could confuse the agent. Still, the core purpose is discernible.

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?

No guidance on when to use this tool versus its siblings (e.g., get_dysfunction, review_stats). There is no mention of prerequisites, context, or alternatives, making it hard for the agent to choose correctly.

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