score

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

With no annotations, the description carries the full burden. It discloses level ordering and the return payload (expected score, legend, calibrated confidence, per-level probabilities), but it does not mention side effects, model parameter behavior, error conditions, or what the instructions parameter controls.

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 compact and front-loaded with the core purpose, followed by a useful example and return summary. There is no filler, though the phrase 'one score question' is slightly terse.

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?

The output schema likely covers the return structure, so the description's return summary is helpful but not strictly necessary. However, it omits guidance on when to choose score over sibling tools and leaves two parameters unexplained, making it adequate but incomplete.

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%, so the description must compensate. It explains levels and their ordering, but leaves state, instructions, and model semantically undefined in both the schema and description. This is only partial compensation.

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 operation: rating a state on an ordinal scale using ordered levels. It emphasizes 'one score question' and 'ordinal scale,' which distinguishes it from categorical classification, though it doesn't explicitly name sibling alternatives.

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 implies use for ordinal scoring but provides no explicit guidance on when to use this tool instead of siblings like classify, decide, triage, or check. There are no stated exclusions or alternative selection criteria.

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