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

Annotations already declare readOnlyHint=true, so safety is covered. The description adds real behavioral value beyond that: the FHIR resource path and the key insight that returned entries reference a separate Binary retrievable via get_binary. It omits pagination/rate/auth details, but for a read-only list tool this is solid additive context.

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?

Three short, front-loaded sentences with zero waste: purpose, endpoint, and follow-up action in order of importance.

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?

No output schema exists, yet the description explains what each entry represents and how to fetch the actual document, which is the essential missing piece. It does not describe item-level fields or pagination behavior, leaving a minor gap for a tool with a fully documented input schema.

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 schema already documents patient_id, type, and _count. The description adds no syntax or format detail (e.g. LOINC system|value format) beyond the schema, so baseline 3 applies.

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?

Specific verb+resource ('List a patient's document references') with examples (C-CDA, notes) and the underlying FHIR endpoint (GET /DocumentReference?patient={id}). This clearly distinguishes it from sibling list_* tools that target allergies, conditions, observations, etc.

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?

Explicitly routes the agent to the natural follow-up tool: 'Each entry points at a Binary you can fetch with healthgorilla_get_binary,' establishing a two-step workflow. It does not state when-not-to-use or contrast with the sibling list_* tools for other resource types, so it stops short of full 5-level guidance.

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