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

Annotations already signal read-only, but the description adds non-obvious behavior: every active guest is returned in one response, there is no paging, ordering is unspecified, removed guests are excluded, and invite_url stays null until publication. These are behavioral caveats an agent could not infer from the schema or annotations. There is no contradiction.

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 dense at around 140 words, but every sentence earns its place: scope, response behavior, publish caveat, filtering behavior, ID sourcing, downstream tool IDs, and alternative routing. The primary use case is front-loaded, with caveats and routing details following naturally. No filler or redundant restatement 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?

With an output schema present, the description does not need to re-enumerate return fields. It covers input sourcing, filter semantics, important behavioral caveats, and the alternative tool for counts, which is everything an agent needs to call it correctly. The description is complete for a read-only list operation of this complexity.

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 the baseline is already high, and the description adds meaning beyond it: it tells the agent where to obtain event_id and interprets rsvp_status=pending as 'who has not responded'. It also explains that omitting rsvp_status lists everyone, which reinforces the schema without restating enum definitions. This is modest but useful added value.

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 leads with a specific use case: seeing who is on a Lemonvite invitation and how each guest responded, then enumerates the returned fields. It clearly distinguishes itself from siblings by describing itself as a guest-listing operation and even points to the count-summary alternative. It is not a tautology of the title and gives an agent enough to identify the right tool.

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?

It explicitly says when to use the tool ('Use this when the user wants to see who is on a Lemonvite invitation...') and when not to ('For counts only, use lemonvite_get_rsvp_summary instead'). It also provides operational routing: get event_id from lemonvite_list_invitations, and note that each guest's invitation_id is what update/remove tools consume. This is strong guidance for tool selection and sequencing.

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