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

Annotations already declare openWorld and destructive, but the description adds the non-obvious failure mode: "The API can return success without adding a guest," which the annotations cannot convey. It also concretizes the destruction as unsendable email plus trip-data exposure to external recipients. The closing sentence partially restates the hints rather than adding new facts, keeping it short of a 5.

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?

Front-loaded with purpose and usage, then safety, which is the right ordering for a destructive tool. The safety block is slightly padded: "This applies even when invitations are optional or a favorite guest is added directly" re-states the destructive hint in a way that costs words without new 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?

Covers purpose, preconditions, ordering (check collaborators after), silent-success risk, and external side effects; an output schema exists so return values need no explanation. Nothing material is missing for calling this correctly and safely.

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 3, but the description adds real meaning for invited_user_email: confirmed favorites can be added directly, which tells the agent that a known favorite address takes a different path than an arbitrary invite. It does not clarify how the permissions sub-fields interact with the inviter's own limits beyond what the schema already says.

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?

States a specific verb and resource ("Invite a guest to an existing trip by email") and immediately scopes it against a near-neighbor workflow ("guest_invites is only processed during trip creation"). An agent can distinguish this from tripsy_collaborators_list/update/delete without opening a 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?

Explicitly says when to use it (existing trips) and when not (creation flow), and gives the operative precondition ("Requires permission to add guests"). It also names the follow-up action after calling ("check collaborators afterward"), so the agent knows the tool is not self-verifying.

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