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

Annotations are all false (readOnly, openWorld, idempotent, destructive), so the description must carry the behavioral disclosure. It does so by stating that the invitation 'arrives as a draft and publish_invitation puts it live,' which clarifies the side effect of creation (draft only) and the need for a separate publishing step. It also explains that the template id is fixed once published, a meaningful behavioral trait. It doesn't disclose any destructive implications, but none are expected for a create tool.

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 verbose, running into a lengthy second paragraph about pre-wedding and wedding-day functions. While informative, this detail could be condensed or moved to a later position; the core purpose and usage guidance are front-loaded, but the extended enumeration of ceremony types adds bulk. It earns a mid-range score because the structure is still logical and the content is relevant, but it is not as lean as it could be.

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 tool's complexity (nested objects, 2 required params, an existing output schema), the description covers the essential context: what it creates, when to use it, the template requirement, and the draft/publish flow. It doesn't describe error conditions or return values, but those are adequately handled by the output schema and the assumed behavior of a create operation. It is sufficiently complete for an agent to invoke it correctly.

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 description coverage is 100%, so the schema already documents each parameter. The description adds value beyond that by highlighting that templateId is required and that the programme lists are flexible ('the lists record only what is supplied'), clarifying that the agent should only include ceremonies the couple actually holds. This contextual nuance compensates for the otherwise generic schema and makes the parameters more usable.

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 clear, specific statement of what the tool does: 'Create an interactive invitation: an animated page on its own link with an opening scene, scratch-to-reveal, countdown, venue map and RSVP.' It then explicitly contrasts itself with the sibling create_form ('not a questionnaire... which is what create_form builds'), making the purpose unambiguous and distinguishing it from the closest alternative.

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 goes beyond stating purpose to give direct usage guidance. It names create_form as the alternative for questionnaires and provides a concrete rule: 'A request for a "wedding invitation form" describes this page rather than a questionnaire.' It also points to list_invitation_templates for the required template id and to publish_invitation for making the draft live, giving the agent a clear workflow context.

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