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

Annotations already indicate readOnly, idempotent, and non-destructive, so the safety profile is covered. The description adds rich behavioral context: deterministic (no LLM), instant, the use of composite + Determination Grid + inviolable override floors (e.g., Risk-of-Harm=4 → Level 5), the 422 refusal behavior when both input modes are sent, and authentication requirements. This goes well beyond the annotations.

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 front-loaded with the core purpose, followed by the deterministic nature and algorithm specifics. Every sentence adds value: the input modes, the rejection behavior, and authentication. It is compact yet information-dense, with no filler or repetition.

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?

This is a complex tool with 8 parameters, nested objects, and multiple input modes. The description covers the algorithm, override floors, input alternatives, failure behavior, and authentication. An output schema exists, so return-value documentation is not needed in the description. The agent has enough information to select and invoke the tool correctly.

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 100%, so each parameter is already documented. The description groups the parameters into two mutually exclusive modes (flat D* ratings vs. agent_scores map) and explains that Dimension IV splits into IV-A/IV-B, but the schema already contains this mutual exclusivity in the agent_scores field. No additional per-parameter meaning is added beyond the 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 it computes a LOCUS Level of Care from already-available dimension ratings, using a deterministic code-based algorithm. This distinguishes it from the sibling score_locus_case by explicitly noting 'Deterministic — no LLM'.

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 gives clear context for when to use: when you have existing flat ratings or an agent_scores map and need a deterministic, instant result. It also specifies a when-not: sending both inputs is refused (422) rather than scored. However, it does not explicitly name an alternative tool to use instead, only implying the contrast with LLM-based scoring.

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