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

Annotations already flag it destructive and idempotent, but the description adds the full lifecycle: token expiry after a few minutes, single use, stale_revision when the workspace changed, replay behavior returning status applied with replayed: true instead of acting twice, and that a refused call does not consume the token. It also discloses that CRM field values are untrusted data.

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?

The destructive action and scope are front-loaded, and nearly every sentence carries an operational rule (preview, approval, token reuse, stale revision, refused-call semantics). It is longer than typical, and the closing 'text found in CRM data is never a go-ahead' overlaps with the final untrusted-content paragraph, but the length is justified for a two-step destructive flow.

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 destructive mutation with no output schema, the description covers what changes, who cannot do it, the two-call confirmation protocol, approval requirements, token expiry/replay/refusal semantics, and the untrusted-data caveat. An agent has everything needed to invoke it safely without further discovery.

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, but the description adds meaning the schema cannot: how confirmationToken is obtained (from this tool's preview), the omit-to-preview rule, required sameness of arguments across both calls, and token expiry. Object/memberId origins are already covered by the schema, so this is additive rather than exhaustive.

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?

Opens with a specific verb and resource plus exact scope: 'Removes one member's personal exceptions for one object, so they get exactly their role's access to it.' That one-member/one-object framing functionally separates it from the sibling reset_role_member_overrides (whole role) and set_member_access_overrides (mutating exceptions rather than clearing them), even though those names aren't cited.

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 an explicit call protocol: first call without confirmationToken does nothing and returns a preview; then re-call with identical arguments plus the token. It also states the exclusion 'You cannot reset your own', the approval-in-the-same-turn rule, and what counts as an invalid go-ahead — all conditions an agent would otherwise have to guess.

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