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

Annotations already establish readOnly, idempotent, and non-destructive, so the bar is lower. The description adds genuinely new behavior: the result is sorted newest first and the invitation link/token is deliberately withheld (delivered by email instead), which prevents an agent from expecting a token it can reuse.

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?

Two short sentences, both front-loaded with the most important facts: scope first, then ordering and the link caveat. No filler or restatement of the title.

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 carries the burden of return-shape hints and does credibly cover ordering and the one field that is never returned. It does not say what fields invitations do contain (invitee email, role, sent date), which is the remaining minor gap for a no-schema read tool.

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?

The tool takes zero parameters, so the baseline is 4 and there is no parameter syntax for the description to compensate for. There is nothing the description could add here beyond noting the absence of filters, which it does implicitly by describing a fixed 'open' set.

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+resource (list invitations) and then pins down the scope of 'open' as 'nobody has accepted yet', which is exactly the distinction an agent needs against siblings like cancel_invitation, resend_invitation, and invite_member. Ordering (newest first) and the dashboard-UI equivalence further remove ambiguity.

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 'open invitations' scoping and the 'as the dashboard's Team page shows them' framing tell the agent clearly when this tool applies. It stops short of naming when-not to use it or routing to alternatives such as list_organization_members, so it is clear context without explicit exclusions.

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