Check action policy

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

The description repeatedly states 'Read-only' and 'ADVICE ONLY. nable never applies the action,' but the annotations declare readOnlyHint: false (i.e., not read-only). This is a direct contradiction between the description and structured metadata. The tool's safety profile is misrepresented, so the agent cannot reliably assess side effects.

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?

The description is longer than necessary but well-structured with line breaks, bullet-like verdicts, examples, and trigger phrases. It front-loads the core purpose and each section adds useful context. Minor redundancy exists ('ADVICE ONLY' appears twice), but overall it remains organized and readable.

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?

The tool has 7 parameters and no output schema, so the description needs to explain behavior. It covers the verdicts, policy knobs, and action_type examples, making the tool's behavior understandable. It does not detail the exact meaning of every parameter (handled in parameter_semantics) and omits response format, but for an advisory policy gate, the description is largely adequate.

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?

With schema description coverage at 0%, the description must compensate. It explains the role of 'action_type' and mentions optional cost inputs (Terraform plan, helm diff, monthly delta), but it does not map these to the parameter names like tf_dir, terraform_plan_file, terraform_plan_json, or budget_name. This adds partial value but leaves several parameters ambiguous.

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?

The description clearly identifies the tool as an 'Advisory policy gate' that returns a verdict (allow/escalate/block) for proposed remediation actions. It uses specific verbs and resource names, and the examples of action types and triggers distinguish it from siblings like estimate_change_cost or check_ai_budget.

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?

The description provides explicit good triggers ('can the agent do X', 'is this action within policy') and concrete example queries. It clearly indicates this is the propose-only check before a human applies an action. It does not explicitly name alternatives or say when not to use this tool, but the context is strong enough to infer appropriate usage.

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