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

Beyond the readOnlyHint annotation, it discloses that the score is computed live, explains the two axes, states the refusal behavior for unreachable clusters ('answers a refusal naming the cause'), and preempts the misleading perfect-score reading when total_workloads is 0. That is meaningful behavioral context the annotation does not 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 core purpose and the two axes, followed by the important edge cases. It is dense and slightly run-on as a single paragraph, but every clause (0-100 range, two axes, read-only, zero-workload caveat, refusal behavior) earns its place.

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 steps in to describe the return shape: two 0-100 axis scores plus 'the workloads that pull it down and what to tighten'. It also covers failure behavior. It is nearly complete, though the precise structure of per-workload detail is left somewhat vague.

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 documents cluster_id's UUID format and that it is optional when conversation-bound, so the schema does the heavy lifting. The description adds only the scope phrase 'of one cluster' and no format or binding nuance beyond the schema, making baseline 3 appropriate.

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: the NetworkPolicy over-privilege score of one cluster, computed live, broken into ingress and egress axes scored 0-100. This distinguishes it from siblings like get_cluster_policy_violations and get_service_cluster_policy without needing to open 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?

Usage context is implied by the metric description, and the 'total_workloads 0 means nothing to score' note clarifies interpretation. However, it never names an alternative tool or states explicitly when to reach for this versus other cluster-security siblings, so routing remains inferred.

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