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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description earns credit for disclosing what the call actually returns — allergies, medication history, preferred pharmacies, and nested prescriptions/orders as ids plus states — and for naming the underlying GraphQL field. It omits any note on authorization or on how large those nested collections can get.

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?

One densely packed sentence with the resource constraint first and the returned data second, plus a terse source mapping. Nothing is padded and nothing needed is buried.

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 correctly shouldered the burden of describing the return shape and did so concretely. Remaining gap is behavioral rather than structural: no mention of pagination or size limits on the bundled prescriptions and orders, which an agent calling this for a heavy patient would want to know.

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% and the single parameter is fully documented as a "Photon patient id (pat_…)". The description's "by Photon id" adds no meaning beyond the schema, so the baseline of 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 plus the identifier type ("Get one patient by Photon id") and enumerates the payload contents, so the agent knows this is a single-record fetch rather than a list. It implicitly separates itself from photonhealth_list_patients, but never names a sibling explicitly.

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?

Usage is only implied: the phrase "by Photon id" tells the agent it needs a `pat_…` identifier, which rules out the search-oriented tools. There is no explicit when-to-use, when-not-to-use, or named alternative for the many nearby record-fetch tools (get_order, get_prescription, get_pharmacy).

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