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

Goes well beyond readOnlyHint=true by disclosing a non-obvious side effect: it 'records a finished run or dry run it finds, so the answer never trails the operations it reports' while explicitly assuring nothing on the cluster is touched. It also defines the security_lag tri-state (behind / unknown / not the same as none), which is genuine behavioral nuance the 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-loaded with the resource and then a dense, well-ordered enumeration of the reported facets; each clause earns its place. It is longer than typical, but the length is driven by the breadth of state being reported rather than 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?

With no output schema, the description carries the full return-value burden and does so thoroughly, spelling out policy fields, per-host run steps, dry-run state, and the security_lag values. Nothing an agent needs in order to call or interpret this tool 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?

Both cluster_id and cluster_name are fully documented in the schema (100% coverage), so the baseline is 3. The description adds no selector semantics beyond what the schema already provides, e.g. precedence between the two optional identifiers.

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 ('Report the rolling OS security-patch lane's state') and enumerates exactly what is covered: patch policy, newest run with per-host steps, last dry run, and security_lag. An agent can distinguish this read-only reporting tool from run_os_patches / plan_os_patches / set_os_patch_policy without opening a 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?

Usage is implied rather than stated: the closing line 'A plain read: nothing on the cluster is touched' signals it is the inspection counterpart to the mutating patch tools, but no sibling is named and no explicit when/when-not is given. Adequate but leaves the agent to infer the read-vs-act routing.

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