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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered structurally. The description nevertheless adds meaningful behavioral context beyond them: result ordering and the security-relevant guarantee that the raw token is never included.

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 sentences, zero filler. The scope/ordering fact leads, with the usage hint and the token guarantee following — appropriately front-loaded for an agent scanning for a match.

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?

An output schema exists, so return values need no explanation, and annotations cover the safety profile. The remaining gap is minor: no mention of pagination or status filtering, which an agent might reasonably expect from a list endpoint.

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 0% for two parameters, so the description must compensate. It implies the tenant scope ('caller's tenant'), which suggests how tenant_id behaves, but never explains tenant_id's default/empty-string semantics or the authorization parameter's role.

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'), scopes it to the caller's tenant, and specifies ordering ('most recent first'). The status enumeration (pending, accepted, revoked) makes clear this is a read-only overview, cleanly distinct from the create/revoke/accept siblings.

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 a concrete usage context: 'Call this to show a tenant admin which invitations are pending, accepted, or revoked.' It does not name an alternative tool or state when not to use it (e.g., vs. list_members), so it stops short of full routing guidance.

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