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

Annotations already declare destructive=true, readOnly=false and non-idempotent, so the safety profile is covered; the description adds the authorization model and the self-revocation restriction for elevate holders, which is real value beyond the annotations. It does not state whether revocation takes effect immediately or whether it can be undone, so it stops short of full behavioral disclosure.

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?

Four short sentences, front-loaded with the action and followed by preconditions, and every clause carries information an agent needs. Slightly dense punctuation-heavy prose but no filler sentences.

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 destructive mutation with no output schema, the description covers permission requirements, the elevate-holder restriction, the org-role exclusion, and where to obtain grant_id. The main remaining gap is post-call behavior — whether the grant disappears immediately and how to re-grant — but nothing required for correct invocation is missing.

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% and the schema already explains that grant_id is a UUID from list_cluster_access_grants, so the description's restatement adds little. Nothing is said about cluster_id vs cluster_name beyond what the schema's 'optional when a cluster is selected' already conveys, leaving parameter semantics at the baseline.

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 and resource ('Revoke one Kubernetes access grant on a cluster') and bounds the scope to a single grant. The CLI twin reference and the mention of grant_id source make it unambiguous which object is affected, distinguishing it from siblings like revoke_security_disposition or elevate_cluster_access.

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 names the required permission (kube_access.manage), the narrower case for elevate holders (only their own elevation), and a when-not case: grants carried by an organisation role cannot be revoked here and the member's role must be changed instead. That is a clear when/when-not routing rule rather than implied usage.

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