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

Annotations already declare destructiveHint=true, openWorldHint=true, and idempotentHint=false. The description adds context those annotations cannot convey: that it is an external side effect and that it requires approval, plus the temporal nature ('time-limited') of the invitation path. It does not explain reversibility or what 'destructive' means for sharing, keeping it below a 5.

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, front-loaded with the action and followed by the behavioral constraint. No filler and nothing redundant.

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 not be described, and annotations cover the safety profile. However, for a destructive, approval-gated mutation with 80% undocumented schema parameters, the description leaves the optimistic-concurrency parameter and the approval workflow underspecified.

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 only 20%, and the description does not compensate: expectedAclVersion, a required concurrency/optimistic-locking token, is never explained, nor is how role values map to behavior. It adds only a hint about the email parameter's two modes, leaving most of the five required parameters opaque.

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 (grant access / email invitation) and captures the two-mode nature of the operation, which reliably separates it from siblings like sheets_update_user_access and sheets_resend_invitation. It stops short of explicitly naming the alternatives, so it does not reach a 5.

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 two branches ('existing verified user direct access' vs 'time-limited invitation') imply when each path applies, which is useful, but the description never states selection criteria, prerequisites, or how this differs from sheets_update_user_access, sheets_set_team_access, or sheets_resend_invitation.

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