score_rubric

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

With no annotations, the description fully discloses behavioral traits: expects scores 0-100, default weights, renormalisation across active agents, returns weighted_score, per-dimension breakdown, pass/fail vs default threshold 75, and ASCII scorecard. No contradictions.

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 sentences: first states core purpose, second adds weight/threshold details, third explains renormalisation and outputs. Every sentence adds value, no redundancy, front-loaded with purpose.

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 3 parameters, no output schema, and nested objects, the description covers inputs (scores, weights, threshold), behavior (weighting, renormalisation), and outputs (weighted_score, breakdown, pass/fail, ASCII card). It handles the partial advisory pass special case, making it complete for an agent selecting this tool.

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?

Despite 0% schema description coverage, the description adds meaning by explaining each dimension corresponds to an agent, scores are 0-100, weights have defaults overridable via .squad.yaml, and threshold defaults to 75. It could detail the weights object structure (only allowed agent names) but provides substantial semantic value beyond the raw 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 clearly states the tool computes a weighted multi-dimensional rubric scorecard from per-agent advisory scores, distinguishing it from sibling tools like score_risk by focusing on rubric scoring with multiple dimensions and pass/fail threshold.

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 context on when to use (computing scorecard from per-agent scores) and explains key features like default weights, overridable weights, and renormalisation. However, it does not explicitly state when not to use or mention alternative tools, though the context is sufficient for most use cases.

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