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

Goes well beyond the readOnly/idempotent/non-destructive annotations by disclosing edge-case behavior: unknown symptom keys fall back to returning the symptom list, and `description` matches only on a verbatim label or alias. It also clarifies the non-obvious constraint that no records are read, preventing misuse. These are genuine behavioral disclosures an agent could not infer.

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?

Well front-loaded: purpose, then accepted inputs, then coverage, then return shape, then edge cases. The prose re-enumeration of symptom labels partly duplicates the schema's own examples/known-keys list, which is the only waste, but the ordering makes it easy to scan.

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 a rich output schema, full annotation coverage, and 100% parameter description coverage, the description supplies the remaining missing pieces: the fallback behavior for unmatched input and the no-record-read boundary. Nothing needed to invoke it correctly is absent.

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%, so the baseline is 3, and the description adds real meaning on top: it explains that neither symptom nor program/participant IDs are mandatory and defines the resolution order between `symptom` and free-text `description`. It does not elaborate on campaignId/participantId/participantEmail beyond what the schema already says.

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 (Diagnose) and resource scope (referral tracking and program problems), then explicitly carves itself out from the record-reading siblings with 'It does not read program or participant records.' An agent can distinguish this from get_campaign_analytics or get_participant without opening any schema.

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 clear usage context ('Accepts a symptom or description without requiring a program or participant ID') and enumerates the concrete situations it covers. It also implicitly signals when-not-to-use by noting it does not read records, but it never names a specific alternative tool (e.g., analytics tools for number mismatches), so routing is slightly inferential.

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