Delete ACL

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

Annotations already flag destructive/non-idempotent, but the description adds materially more: it elevates the session to security_admin (scoped only to ACL tools), captures writes into a named update set with read-back verification, and deactivates an active ACL first before deleting, reactivating it if the delete fails. These are non-obvious side effects an agent could not infer from the annotations.

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?

It is front-loaded with the action, then the safety gate, then the alternative, which is the right order for an agent. Some sentences are heavily packed (the elevation and write-verification clause), so it is dense rather than wasteful.

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 7-parameter destructive mutation with no output schema, the description covers the safety gate, privilege elevation, update-set capture, verification, and failure recovery. An agent has enough to call it correctly and to understand the consequences without a return-value contract.

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 real meaning about update_set (writes are captured and verified there, the user's own current update set is untouched) and about confirm's intent via the approval step. It does not add syntax detail for scope/scope_id/instance, which the schema already handles.

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?

"Delete an access control and its role rows" gives a specific verb plus resource and even names the cascade (role rows). It is immediately distinguishable from create_acl, update_acl, remove_acl_role and delete_metadata_record.

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?

It names the preferred alternative explicitly ("Prefer update_acl with active=false, which is reversible, unless the user asked to delete") and states the pre-call obligation to tell the user who gains or loses access and get approval. Both the when and the when-not are spelled out.

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