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

Beyond the annotations (readOnlyHint=true, idempotentHint=true, openWorldHint=false), the description discloses critical runtime behavior: partial success with `found` and `notFound` fields and per-code reasons, malformed NDC handling, auto-detection, the `childrenTruncated` flag, and the `alsoInSystems` collision signal. It also explains the impact of `includeHierarchy` and how to walk the full set. This goes well beyond the annotations, giving an agent a precise mental model of the tool's behavior.

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 long but every sentence earns its place, covering the core action, NDC specifics, batch semantics, hierarchy option, collision handling, and chaining. It is front-loaded with the primary purpose, then branches into details. No redundant or filler language—each clause contributes to actionable understanding.

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 (multiple coding systems, NDC decoding, partial success, hierarchy, collisions) and the presence of an output schema, the description covers all necessary aspects: input constraints, optional parameters, edge cases, and secondary behavior. It even mentions the `alsoInSystems` field and the `childrenTruncated` flag, which are likely part of the output schema but are reinforced here. An agent can fully anticipate how to call the tool and interpret results without further inspection.

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?

Even though the schema has 100% coverage with descriptions for each parameter, the description adds meaningful detail: it specifies exact NDC segment formats (4-4-2, 5-3-2, 5-4-1, 5-4-2, and bare 10/11 digits), clarifies that the `codes` array accepts mixed systems, and explains that `system` is only for forced lookups. This adds semantic value beyond the schema, particularly around edge cases and expected input formats.

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 opens with a specific verb and resource: 'Decode one or more US medical codes to their official descriptions' across multiple named systems (ICD-10-CM, ICD-10-PCS, HCPCS, RxNorm). It distinguishes itself from siblings by covering decoding specifically, and further differentiates NDC decoding as a unique behavior. The description is clearly about a batch decoding tool, not a search, map, browse, or check tool.

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 explicitly states when to pass the `system` parameter ('only when a value is genuinely ambiguous'), and directs users to alternatives for fuller hierarchy traversal ('walk the full set via medcode_browse_hierarchy or medcode_map_codes'). It also mentions chaining into medcode_map_codes or a billability check, providing actionable routing. This is clear, specific guidance that selects this tool over siblings.

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