scf_delete_engagement

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

With no annotations provided, the description carries the behavioral disclosure burden. It clearly labels the operation as destructive, requires admin role, states that no content is returned on success, and reveals that auditor access is revoked. It does not explicitly mention irreversibility or all downstream cascade effects, but the core destructive behavior is well disclosed.

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 description is two tight sentences with no filler. It front-loads the primary action and scope, then adds permission, response, and side-effect information. Every clause adds operational value.

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 2-parameter delete operation with fully documented parameters and no output schema, the description is complete: it states what is deleted, the authorization required, the success response, and an important side effect. An agent has enough information to select and invoke this tool safely.

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?

The input schema covers both parameters with 100% description coverage, so the tool description does not need to add parameter meaning. The schema already explains that org_id comes from scf_list_organizations and engagement_id from scf_list_engagements. Baseline 3 is appropriate because the tool description itself adds no parameter-level detail.

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 specific verb and resource: 'Delete an audit engagement and its frozen scope.' It clearly identifies the target resource and the destructive nature of the operation. The scope mention also distinguishes this from sibling engagement tools such as scf_update_engagement and scf_remove_engagement_auditor.

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 description states a key prerequisite ('admin role') and frames the operation as a destructive write, which implies use when an engagement must be removed. However, it does not explicitly contrast this with alternatives like scf_remove_engagement_auditor or state when not to use it. Usage context is implied rather than explicitly guided.

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