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

Annotations only give a coarse safety profile (destructive, non-idempotent, not read-only); the description adds substantive behavior: self-replacement, a transient offline window of seconds, the default version resolution that never moves an agent backwards, and explicit refusal conditions for bad versions. That is exactly the context annotations cannot carry.

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?

Front-loads the action and the fleet-rollout contrast, then layers version semantics, refusals, preconditions, and permission. Dense but every clause is load-bearing; the parenthetical about release candidates is a slight excess.

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?

With no output schema, the description still covers outcome (agent re-rendered/restarted), transient impact (cluster reads offline for seconds), preconditions, permission, and failure modes. 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 baseline is 3, but the description adds real semantics the schema does not: the interaction between version and allow_downgrade, what happens when version is omitted, and when a downgrade is refused. The cluster_id/cluster_name selection semantics are left to the schema.

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+resource+immediacy ('Upgrade the Ankra agent on a cluster now') and explicitly contrasts it with the fleet rollout path, which is what distinguishes it from set_cluster_agent_auto_upgrade and upgrade_cluster. An agent can route to this tool without opening the 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?

Explicit preconditions are given: check get_cluster_agent_status first, the cluster must be online, and it must have exactly one registered agent; permission requirement (agents.manage) is named. It also tells the agent how to handle refusals ('relay those refusals as they are'), which is actionable guidance rather than inference.

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