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

Annotations already declare readOnlyHint=false, destructiveHint=true and idempotentHint=true, so the safety profile is carried structurally. The description adds genuinely new behavioral context: the response shape (id, name, clinic, changed fields) and the privacy rule that contact details are never returned. It omits what happens to fields not supplied, which is the remaining gap.

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 with zero filler: trigger first, return behavior second, exclusion third. Every sentence carries distinct information.

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?

An output schema exists, so the description need not explain return values, yet it usefully does. The one missing piece for a mutation tool is whether a call with no optional contact fields is valid and whether omitted fields are preserved, which matters given the destructiveHint.

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 each parameter carries its own description, including the optimistic-concurrency meaning of expectedLastEditTime. The description adds nothing about parameters beyond echoing which fields are editable, 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?

Names a specific verb ('change') plus the exact resource fields it touches (name, phone, email, language) and explicitly excludes medical history and other patient details. An agent can distinguish this from create_patient and find_patient without opening any schema.

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?

The opening clause gives an explicit trigger condition ('when someone asks to change a patient's name, phone, email or language') and the closing sentence states a negative boundary. It stops short of naming that create_patient is the alternative for new records, but the trigger and exclusion are clear.

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