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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description adds crucial behavioral detail: the invitee gains no powers until acceptance, the invitation expires after 7 days, acceptance auto-joins them at the offered role, and authorization requirements for performing the action. This is exactly the kind of non-obvious behavior an agent needs to know.

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 compact and front-loaded: first sentence states the primary action, the second sentence covers the most important behavioral effects and requirements, and the third sentence points to the undo path. Every sentence adds value; there is no filler or redundancy.

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 moderately complex mutation tool, the description covers the core operational facts: immediate effect, expiry, permission prerequisites, role restriction, and how to reverse it. It does not mention error cases (e.g., already invited, invalid user) or how to list existing invites, but with an output schema present and the schema already documenting parameters, these are minor gaps. A small deduction for not clarifying the apparent contradiction that `colony` is described as 'Required.' but is not in the schema's required list.

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% and each parameter already has a descriptive comment. The description mostly restates the `role_offered` restriction ('offering admin is founder-only') that is already in the schema's enum description, and it does not add meaningfully new semantics for `colony`, `invitee_username`, or `permissions`. It provides some lifecycle context (no powers until accept, auto-join), but that is behavioral rather than parameter-specific, so a baseline 3 is appropriate.

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: 'Invite a user to join a colony's moderation team.' It also names the companion tool for the reverse operation (`colony_revoke_mod_invite`), which helps distinguish it from related mod-management tools. The purpose is unambiguous and easily differentiable.

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 clear invocation context: it states required permissions (founder/site-admin/can_manage_mods), a special restriction (admin offers founder-only), and an explicit alternative for when to withdraw a pending invite. It does not, however, explicitly contrast with other mod-member tools like `colony_set_member_role` or `colony_respond_mod_invite`, so it falls just short of fully comprehensive when-to-use guidance.

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