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

The description adds substantial context beyond the annotations: the confirmationToken requirement, the preview_operation gating flow, the required permission and role, and the observable effect on the invitation link. What it does not cover – whether the invitation can be reinstated, rate limits, or post-cancel audit behavior – is minor for a single-item cancel. Well above the bar set by the destructiveHint annotation.

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?

Three dense sentences, front-loaded with the action and its effect, then id discovery, then the required confirmation procedure. No filler, and each clause carries operational value for a destructive tool.

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?

Given this is a destructive, multi-step-confirmation operation with an output schema that handles return values, the description covers the critical missing pieces: the confirmation gate, the permission requirement, and how to source the id. Fully adequate for correct invocation, though it could note idempotency guidance for the optional requestId.

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 25% (only requestId is documented), so the description must compensate. It successfully explains confirmationToken's workflow role and where to find invitationId, but says nothing about organizationId or the idempotency semantics of requestId beyond what the schema already states.

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 ('Cancel a pending invitation') and immediately clarifies the consequence ('its link stops working'). This distinguishes it clearly from siblings like invite_member or update_member, and an agent knows exactly what effect to expect.

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?

Explicitly tells the agent how to obtain the required id ('Find ids with list_members and includeInvitations') and prescribes the pre-execution workflow ('call preview_operation ... show the returned plan ... call this tool only after the user explicitly agrees'). Prerequisites (organization:manage permission, owner role) are also stated, leaving little to inference.

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