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

Strong disclosure beyond the thin annotations: write semantics, non-idempotency with the concrete consequence ("calling twice creates two patients"), downstream side effect on patient messaging via the practice's settings, and a health-data handling rule. The only gap is no statement of what the call returns or what permissions are needed.

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?

Five short, front-loaded clauses, each carrying distinct information: write scope, duplicate check, messaging side effect, idempotency, data-handling rule. No sentence is redundant.

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 28-param mutation with no output schema and minimal annotations, it covers purpose, ordering, side effects, and compliance well. It stops short of telling the agent whether the created patient's id is returned for chaining into splose_get_patient, and leaves most optional fields uncharacterised.

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?

With 28 parameters and only 36% schema description coverage, the description carries a heavy burden it mostly does not meet. It clarifies required names and explains communicationPreference's interaction with organisation settings, but the majority of fields (address block, Medicare/NDIS identifiers, phoneNumbers structure, invoiceRecipientId) get no added meaning.

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?

"WRITE: adds ONE new patient record (first and last name required)" gives a specific verb, resource, cardinality, and the required fields. This clearly separates it from splose_create_contact and from read-side siblings like splose_get_patient.

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?

It names the alternative explicitly — "Search with splose_list_patients first to avoid a duplicate" — giving a concrete precondition before invocation. It also adds a domain constraint ("only enter what the user supplied") that governs what may be passed.

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