score_credit_application

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

With no annotations, the description carries full burden. It discloses the tool is a demo, trained on synthetic data, and methodology is production-style but output is not production. This is crucial behavioral context. It does not discuss destructiveness or auth, but the tool is read-only and no destructive hint is needed.

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?

Two sentences, front-loaded with the action and key outputs. Every word adds value; no redundancy. Perfectly concise.

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 13 parameters, no output schema, and no parameter descriptions, the description is incomplete. It omits return value format, parameter constraints, and usage examples. The demo note partially offsets, but integration still requires guessing input semantics.

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% and the description provides no meaning for any of the 13 parameters (11 required). It does not explain units, valid ranges, or how parameters map to the scorecard. This is a critical gap for correct invocation.

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 uses a specific verb 'Score' with a clear resource 'retail loan application' and explicitly lists outputs (probability of default, scorecard points, letter rating). It distinguishes from sibling tools which focus on portfolio-level risk metrics like VaR, ES, or stress testing.

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 states it's a 'demo model' and 'not a production score', providing context on when to use (scoring single applications) and when not to rely on it (production decisions). It does not list explicit alternatives, but sibling tools are sufficiently different to imply usage boundaries.

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