scf_remove_engagement_auditor

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

The description reinforces the destructiveHint=true annotation by explicitly labeling the operation a 'destructive write' and adds genuinely new context beyond the annotations: the admin-role prerequisite and the 'Returns no content on success' outcome, which is especially valuable given there is no output schema. No contradiction exists with readOnlyHint=false or destructiveHint=true.

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 with zero filler. The primary action and scope are front-loaded, and the parenthetical efficiently packs destructive-write and admin-role context. The return-behavior sentence earns its place because no output schema exists to convey that information.

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 three-parameter tool with no nested objects, complete schema documentation, and safety annotations present, the description is nearly sufficient: it covers scope, auth requirement, and return behavior. The notable omissions are idempotency behavior (does a non-assigned auditor error or no-op?) and a pointer to scf_add_engagement_auditor as the reversal path, both minor for a tool this simple.

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% — all three parameters (org_id, auditor_id, engagement_id) have descriptions in the schema, each cross-referencing the list tool that supplies the UUID. The description adds no parameter-level detail, which is acceptable since the schema already carries the full burden and the baseline is 3 at this coverage level.

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?

The description uses a precise verb ('Revoke') with a specific resource ('an auditor's access to one engagement') and a clear scope qualifier ('one engagement') that prevents confusion with org-wide operations. It is immediately distinguishable from the sibling pair scf_list_engagement_auditors and scf_add_engagement_auditor, even though those siblings are not named explicitly.

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 parenthetical ('destructive write — admin role') implies usage context by signaling this tool requires elevated privileges and should be used only when a permanent access removal is intended. However, it never names the natural inverse alternative (scf_add_engagement_auditor) or states when not to use the tool, leaving the agent to infer the decision rule from the name alone.

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