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

Adds real context beyond annotations: it discloses the walk_pending intermediate return and that it does not finalize an approval. Annotations say readOnlyHint=false, so the agent knows it writes, but the description never says what artifact the score produces or whether it can be re-run safely.

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 declarative sentences, each carrying a distinct constraint, with the core action front-loaded. Nothing is repeated or padded.

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?

Covers the action, the input precondition, and one return state, but with no output schema it should say more about what a score result contains, and it leaves the 'event' parameter entirely unexplained.

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 only 50%, and the undocumented parameter is 'event', which the description never mentions at all – no hint whether it is a trigger label or an event name. Only caseId is indirectly covered by 'facts already on the open case'.

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 and resource: score case facts against the active underwriting pack/rubric. Explicitly bounds the tool with two negatives – it does not accept new facts and does not approve a loan – which separates it from mutating siblings like open_case or start_underwriting_package.

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?

Preconditions are implied clearly: the case must be open and a pack active, and facts must already exist on the case. It doesn't name an alternative tool for submitting new facts (e.g. the walk/chase tools), leaving the redirect to inference.

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