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

Annotations already cover the read-only, idempotent, non-destructive safety profile. The description adds real behavioral context beyond that: quarterly edit vintage disclosure, the absolute-vs-overridable nature of the adjudication indicator, setting-specific limit variation, and CMS NCCI provenance. It doesn't discuss caching, latency, or coverage gaps.

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?

Front-loaded with the core question/answer, then details and examples. Mostly earns its length, though the run of quoted example queries is slightly redundant with the opening question.

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?

With no output schema, the description carries the return-value burden well: it names the MUE units limit, adjudication indicator, rationale, and edit vintage. Combined with the setting coverage note, an agent has everything needed to call and interpret the result.

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 the baseline is 3. The description reinforces that the same code yields different limits per setting, but that is already stated in the setting parameter's schema description, so it adds little 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?

States a specific verb+resource: returns the NCCI Medically Unlikely Edit (MUE) maximum units for a code, with adjudication indicator and rationale. This is clearly distinct from siblings like check_code_pair, explain_ncci_edit, and validate_claim, which an agent can route between without opening schemas.

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 concrete usage contexts via sample questions ("what is the MUE for 99213", "how many units can I bill", "why was my claim denied for units") and notes the three settings with differing limits. It does not explicitly exclude cases better served by explain_ncci_edit or check_code_pair, so it stops short of a 5.

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