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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is fully covered. The description adds genuinely new behavioral context by disclosing the admin-only authorization requirement, which matters for error handling. It says nothing about pagination, result ordering, or result size limits.

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 with zero waste; the scope and status qualifier come first and the permission constraint follows. Nothing to trim.

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 zero-parameter read tool with full annotation coverage, the description supplies the two things annotations can't: workspace scoping and admin gating. The only gap is behavior at scale (pagination/result caps), which is minor given there is no output schema to defer to.

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. The description correctly implies no inputs are needed to scope the call.

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 ('List all invitations') plus the scope ('active workspace') and status filter ('any status'), which distinguishes it from create_invitation and revoke_invitation. It doesn't explicitly name a sibling, but the intent is unambiguous.

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?

'Administrator only' signals a prerequisite, and '(any status)' implies this is the unfiltered enumeration option. However, there is no explicit when-to-use guidance, no mention of how it relates to list_users or list_project_guests, and no note on what to do if the caller lacks admin rights.

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