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

Annotations only declare the generic non-read/non-destructive profile, so the description carries the real weight: it discloses that no token can apply policy, that it records a proposal and returns an apply_url, that an owner/admin must apply it in the web app, that omitted fields are preserved, that null clears bounds, that a new proposal replaces a pending one, that proposals expire after 7 days, and that apply fails on concurrent change. This is exceptional behavioral context beyond 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?

Dense but front-loaded: the core 'this never changes the policy' constraint and the apply_url workflow come first, followed by field/null semantics, then lifecycle/expiry behavior, then the permission. Given the complexity, every sentence earns its place with no filler.

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 complex approval-workflow tool with no output schema, the description covers the return value (apply_url), the caller obligation (hand the link to the user), authentication/permission requirements (kube_access.manage), field-omission and null-clearing semantics, replacement, expiry, and conflict behavior. Nothing an agent needs to call it correctly 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%, so the schema already documents every parameter. The description still adds semantic value beyond the schema by explaining that omitted fields retain current values and that elevated_max_ttl_seconds and require_reason_from_role can be nulled to clear the bound, plus that reason is required.

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 (propose) and resource (organisation cluster access policy), and immediately clarifies what it is not ('This never changes the policy: no token may'), routing the agent to the apply-then-verify workflow. An agent can distinguish it from the read sibling get_cluster_access_policy without opening either schema.

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 clear context on when and how to use it: it is the mechanism to request a policy change, the user must be told to open the returned apply_url, and the required permission is stated. It lacks an explicit 'use X instead of Y' exclusion against any MCP sibling, but the workflow guidance is strong.

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