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

Annotations cover readOnly=false, destructive=true, idempotent=true and openWorld=false. The description goes beyond them by disclosing the return shape (id, name, clinic, language) and a non-obvious side effect: phone and email are stored but never returned. It does not restate the idempotency contract, though the requestId schema already explains it.

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 sentences, each doing distinct work: trigger, return/persistence contract, and exclusion. The usage trigger is front-loaded with zero 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?

With an output schema and 100% parameter coverage, most burden is already carried elsewhere; the description still adds the persistence caveat and the scope exclusion. Minor gaps remain, such as permission requirements or what happens on a duplicate name, but nothing that blocks a correct call.

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%, so all six parameters are already documented, including the requestId dedupe behavior and clinicId/language defaults. The description adds one useful fact about phone/email persist-but-not-returned, but supplies no field-level detail beyond the schema, matching the baseline for fully documented schemas.

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?

The description opens with a specific verb and resource ('add a new patient to their clinic') and adds a boundary ('Not for a patient already on file') that separates it from update_patient and find_patient. It stops short of naming those siblings explicitly, so the agent must infer which tool handles existing patients.

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?

Both a when-to-use trigger ('when someone asks to add a new patient') and a when-not condition ('Not for a patient already on file') are stated. No alternative tool is named, so routing for the existing-patient case is left to inference from the sibling list.

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