Check action policy

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

Explicitly reconciles the readOnlyHint=false annotation ('It is not marked read-only only because tf_dir runs terraform plan there, which executes that directory's provider plugins'), which is exactly the context an agent needs. It also documents the three verdicts (allow/escalate/block), their semantics, the env knobs, and that it never executes anything.

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 core verdict and uses scannable bullets for allow/escalate/block, but repeats the advisory/propose-only message several times ('ADVICE ONLY', 'propose-only guardrail', 'nable does not auto-execute'), which is mild redundancy.

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 usefully defines the return verdicts and their meanings, and it explains the annotation quirk. It falls short on clarifying the four non-cost parameters, which an agent would need before calling with anything beyond the required action_type.

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 0%, so description must compensate. It explains action_type with concrete value examples and groups tf_dir/helm_diff/monthly_delta_usd as the three cost-related inputs, but leaves budget_name, terraform_plan_file, and terraform_plan_json entirely unexplained and doesn't map each cost option to its specific parameter.

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 ('Advisory policy gate: should a proposed remediation action proceed?') and immediately frames the scope as propose-only. An agent can distinguish this from estimate_change_cost or get_cost_summary because it's framed as a policy verdict, not a cost estimate.

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?

Provides explicit triggers ('can the agent do X', 'is this action within policy', 'should I apply this fix') plus examples, which strongly signals when to call it. It does not name sibling tools or state when NOT to use it, keeping it below a 5.

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