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

readOnlyHint=true already declares the safety profile, and the trailing 'Canvas: GET /{resource}' reinforces that this is a read. The description adds useful context about supported resource types but says nothing about result shape, paging defaults, or caps beyond what the schema documents. Adequate but not rich against a lowered annotation bar.

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 with the core action, then sequencing guidance ('Pick resource, then narrow'), then clinical examples. Dense and purposeful, though the run of examples is long enough that it could be trimmed without loss.

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 carries the burden of describing what comes back, and it never mentions that results are a FHIR Bundle or that paging via _count/_offset applies. For a 10-param search tool spanning 35 resource types, that return-shape gap is the main omission.

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 baseline is 3; the description earns above baseline by mapping enum values to clinical meaning (Condition/Observation -> problem list and results, MedicationRequest -> prescriptions, Appointment/Encounter -> visits) and framing the non-resource params as 'standard FHIR search parameters' to be used for narrowing.

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 ('Search any supported FHIR R4 resource in the chart') and scopes the universe of resource types. It does not explicitly contrast itself with siblings like canvas_get_patient_everything (bulk patient fetch) or canvas_read (single-resource read), so sibling differentiation is left to inference.

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 concrete when-to-use guidance ('Nearly every clinical question starts here') and maps clinical intents to resource types (Condition/Observation for problem list, MedicationRequest for prescriptions). It stops short of naming alternatives or when-not-to-use conditions, which keeps it out of the top band.

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