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

Annotations carry only readOnlyHint=true, so the description supplies the missing operational context: it is an authenticated read restricted to OWNER/ADMIN, it caps at 50 records per page, and paging is via nextCursor. Those are exactly the traits annotations cannot express. Return shape is only sketched ('who invited whom, accepted, expiry'), so it is not fully exhaustive.

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?

Dense but front-loaded: access constraint first, then scope, then the revoke cross-reference, then defaults, then paging. Nearly every clause carries information. Minor cost is the terse '本工具（status=PENDING）→' arrow construction, which reads as a note rather than clean prose.

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 read-only, three-parameter list tool with no output schema, it covers access requirements, default vs full filtering, page size, and pagination token — enough to call it correctly on the first attempt. Only the exact returned fields and total-count behavior are left unspecified.

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; the description earns an increment by explaining what status=PENDING vs status=ALL actually include (accepted/declined/revoked/expired) and that nextCursor comes from the previous page. It adds real filtering semantics rather than restating the enum labels.

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 the named member invites *sent by* this organization — and explicitly scopes the content ('who invited whom, accepted or not, expiry'). The 'sent by this organization' framing distinguishes it from the sibling list_my_organization_invites (invites received), which an agent can resolve without opening either 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?

Gives real routing guidance: default behavior is pending+non-expired, status=ALL broadens to accepted/declined/revoked/expired, and revocation is redirected to revoke_organization_member_invite(inviteId). It also states the access precondition (login required, OWNER/ADMIN). It does not contrast with the closest read siblings (list_my_organization_invites, list_organization_members), so it stops short of full when-not coverage.

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