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

Annotations already provide readOnlyHint=false, idempotentHint=true, and destructiveHint=true. The description adds patch semantics—'only the fields provided change; omitted fields keep their saved values'—which informs how all parameters behave, something annotations alone do not convey. It also tells the agent that replacing the invitation graphic requires passing a new invitation_image, but it does not discuss auth or rate limits, so a 5 is not warranted.

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?

The description is two sentences: the first states use cases and the target resource; the second explains the patch model and warns against casual use. Every sentence carries weight, and there is no filler or repetition of the schema.

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?

Given the 25 optional parameters, an output schema, and 84% schema coverage, the definition is still sufficiently complete. It states the patch behavior, the image replacement convention, and the distinction from merely discussing changes. A minor gap is that it does not explicitly summarize 'null clears fields', but each individual parameter's schema description covers that and it is not a blocker.

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 84% schema description coverage the baseline is 3. The tool description adds value by articulating that omission preserves saved values, which is the most important behavior of every update-specific parameter, and it clarifies that a new invitation_image is the way to update artwork. It does not repeat the constraints or enums already documented in the schema.

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 states a specific verb and resource: 'change the details of an existing Lemonvite invitation' and gives concrete examples such as title, description, time, location, host information, RSVP settings, and invitation graphic. Using the word 'existing' clearly distinguishes it from the create_invitation sibling. The closing instruction 'Do not use this merely to discuss possible changes' further narrows the intended trigger.

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 gives an explicit when-to-use phrase and a when-not-to-use clause: 'Use this when the user wants to change the details...' and 'Do not use this merely to discuss possible changes.' This is solid routing guidance, but it does not name alternative siblings such as lemonvite_create_invitation for creating new invites, so it stops just 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.