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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering safety. The description adds behavioral context: 'Deterministic — no LLM, instant' and explains the 422 refusal when both inputs are provided, which is beyond the annotations. It also mentions authentication, which is useful. No contradiction with 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 dense but efficient, front-loading the purpose and core logic before details. It packs essential information into a few sentences without fluff. Each sentence serves a purpose: purpose, determinism, input options, and refusal behavior. Slightly long but justified given the complexity.

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 the tool's complexity (8 params, nested object, no output schema), the description covers the input modes, refusal, authentication, and deterministic nature. However, it does not describe the return value or output format (e.g., the resulting Level of Care as an integer or string). Since there is no output schema, this missing information leaves an agent uncertain about the expected result, which is a notable gap for a compute tool.

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 100% with each parameter described. The description adds the clarification that Dimension IV splits into IV-A Stress and IV-B Support, and reiterates the mutual exclusivity of agent_scores, but the schema already documents these details (e.g., agent_scores description states 'Mutually exclusive with the flat D* fields'). Thus, the description adds marginal value over the schema, fitting the baseline for high coverage.

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 states a specific verb+resource: 'Compute a LOCUS Level of Care from dimension ratings you already have.' It clearly differentiates from sibling 'score_locus_case' by emphasizing it operates on existing ratings, not gathering or scoring from scratch. It also details the deterministic computation approach, making its function unmistakable.

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?

Provides explicit guidance on input modes: 'Provide EITHER the seven flat D* ratings OR a per-reviewer agent_scores map' and warns that sending both results in a 422 refusal. This clarifies when to use each mode and the mutual exclusivity. It does not explicitly name alternative tools (like score_locus_case), but the instruction 'from ratings you already have' implies usage when ratings are pre-existing.

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