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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower; the description still adds real behavioral context: ordering (most recent first), that status is always Pending, that revoke/decline removes rows, and that pagination meta is returned. It does not mention rate limits or result caps, but no contradiction exists.

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?

Purpose is front-loaded and the long return-field enumeration plus lifecycle chain earn their space given there is no output schema. Slightly dense, but no filler or repetition.

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 no output schema, the description compensates by enumerating returned fields (id, email, name, roles, status, created_at, pagination meta) and ordering, and the lifecycle chain makes the tool's place in the invite flow unambiguous. Nothing an agent needs to call it correctly is missing.

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% — both page and page_size carry their own defaults and bounds in the schema — so this is the baseline 3. The description only references pagination meta generally and adds no format or syntax detail beyond 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?

States a specific verb and resource with scope: 'List the authenticated customer's pending invitations — users who were invited... but have not responded yet.' It is distinguishable from sibling list_user_accesses (accepted access) and create_invite_request/cancel_invite_request by name and function.

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 lifecycle sentence explicitly says where this list fits: create_invite_request sends the invite, unanswered invites appear here, cancel_invite_request revokes them, and accepted invites move to list_user_accesses. This gives clear routing context, though it never states an explicit 'use this when you need X' directive or any exclusion.

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