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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds valuable behavioral context: it pins the IPD-IMGT/HLA release, notes it does not store request bodies, and emphasizes the caller's responsibility for de-identification. 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 compact but informative. It front-loads the action and classification categories, then provides usage context and a privacy note. No wasted sentences, though the de-identification instruction could be slightly more concise. Overall well-structured.

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 an output schema exists, return values are covered. The description covers the tool's purpose, classification scheme, use case, constraints (pinned release), and privacy expectations. Nothing essential is missing for an agent to call it 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?

The schema already describes the text parameter thoroughly, and schema coverage is 100%. The description reinforces the parameter's purpose and adds the crucial de-identification instruction, which is not in the schema but is essential for correct usage. This goes beyond the baseline.

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 (scan), resource (HLA typing report text or model output), and the exact classification output (valid/legacy/deleted/fabricated). It explicitly distinguishes itself from interpretation of a case, which differentiates it from sibling tools like check_typing and validate_gl_string.

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 a clear usage context: 'Use on any AI-generated or transcribed content mentioning HLA.' It also gives an exclusion by noting it's 'not interpretation of a case,' which implies it's not for clinical decisions. It doesn't explicitly name alternatives, but the context is sufficient for an agent to select it appropriately.

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