Store a transcript or summary

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

With destructiveHint=true already present, the description adds valuable behavioral context: 'Only supplied fields change' gives partial-update semantics and 'null clears one' exposes the destructive null behavior explicitly. This goes beyond the annotation without contradicting 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?

Every sentence earns its place: the first states the action, the second explains why content must be supplied, and the third gives the exact mutation semantics. No filler and no repetition of schema content.

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 three-parameter mutation with an output schema and annotations already covering safety, the description is complete: it covers source, format, partial updates, and clear semantics. It could have explicitly said that new values overwrite existing stored content, but 'only supplied fields change' conveys this sufficiently.

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?

The schema already describes summary and transcription as markdown-or-null, and the description reinforces that with partial-update semantics: only supplied fields change and null clears. The appointmentId parameter is not elaborated, but coverage is 67% and the description clarifies how the nullable parameters behave.

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: 'Attach ... to an appointment' and names exactly what content is allowed (transcript and/or AI summary in markdown). It also clarifies that the tool is not storing a Meetergo recording, which distinguishes this content-storage tool from recording concepts.

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 description clearly states the tool is used to attach caller-supplied transcript/summary content to an appointment, and the 'meetergo does not record calls' note provides a concrete condition for when this tool is needed. It does not explicitly name alternatives, so it stops short of a 5.

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