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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description adds the meaning of each view mode, but says nothing about auth scope, pagination mechanics, or return content 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?

Front-loaded purpose sentence followed by three usage bullets and a compact Args list; each line maps to an action. The Args block partly restates the usage bullets, which is mild redundancy.

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 should ideally convey what a 'result' actually contains or how history entries are shaped; it only gestures at this ('past diagnoses', 'remaining quota'). Adequate for invocation, incomplete for interpreting the response.

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 only 20%, so the description carries real weight and does document brand_id, diagnosis_id, view, and limit (with 1-100 range and default 20). It omits user_intent, but that param is self-documented in the schema; the only flaw is listing view as 'history' or 'usage' while the enum also allows 'result'.

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 and resource ('Get results of a diagnosis') and immediately broadens to the two auxiliary views it serves. It is distinguishable from write-path siblings like run_diagnosis, though it doesn't name them explicitly.

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 three concrete invocation patterns mapping parameter combinations to intent (diagnosis_id for one result, brand_id+view='history' for past runs, brand_id+view='usage' for quota). Clear context, but no explicit exclusions or prerequisites (e.g., that a diagnosis must exist first).

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