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

Annotations supply destructiveHint=true and the WRITE title; the description adds the async lifecycle (returns query_id, must be polled), the underlying endpoint, and a prominent write warning. It stops short of explaining why the operation is flagged destructive, what permissions or purpose-of-use compliance rules apply, or whether the retrieval is audited or billable.

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?

Two tight sentences plus the endpoint, with the WRITE warning front-loaded and the next-step guidance immediately after the return value. No filler.

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?

For a 4-parameter write tool with no output schema, the description covers the return value (query_id), the polling path, and the endpoint, which is most of what an agent needs. It omits permission/purpose-of-use requirements and the async-vs-sync tradeoff against the get_* siblings.

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 all four parameters (hints, specialties, purpose_of_use, particle_patient_id) with examples. The description adds nothing parameter-specific beyond the patient id appearing in the endpoint path, so the 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?

States a specific verb and resource ('initiate a nationwide clinical-record retrieval for a patient') and implicitly distinguishes itself from the synchronous particle_get_fhir/particle_get_ccda siblings by being a query-creation tool. The WRITE label and endpoint reinforce exactly what the tool does.

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?

Tells the agent the required follow-up ('poll particle_get_query_status for progress'), which is genuinely useful routing. It does not, however, explain when to use this asynchronous query instead of the direct-fetch siblings (get_fhir, get_ccda, get_flat), which is the real selection decision.

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