score_call

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

Adds real behavior beyond the annotations: 'claude' requires ANTHROPIC_API_KEY in the server environment, and the result goes through the same evidence guard as submit_scores and 'is saved only if it passes' — so a call may silently not persist. It does not address the idempotentHint=false implication (re-scoring the same call), which keeps it from a 5.

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 short sentences, front-loaded with the action and scope, then modes, then side effects, then routing. Dense and waste-free, though the quoted-keyword phrasing is slightly packed.

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?

An output schema exists, so return values need no explanation, and the description covers auth, persistence guard, and routing. The only gap is the unexplained rules_version parameter, a minor omission.

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 carry the load. It explains the two scorer enum values and their differing auth/behavior requirements, which is the most important parameter, but says nothing about call_id or rules_version.

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?

States a specific verb+resource ('Score a call on the server') and immediately scopes it to headless/'nobody in the loop' runs, which separates it from the interactive submit_scores path. An agent can distinguish it from all siblings without opening a schema.

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?

Gives an explicit usage condition (runs with nobody in the loop) and an explicit alternative for the other case: 'In a chat, prefer get_call plus submit_scores.' This is exactly the when-to-use vs when-not-to-use routing the dimension asks for.

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