iam_policy_review

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description contributes one genuinely useful trait beyond them — that results are heuristic and superseded by provider analyzers — but says nothing about handling of malformed input, partial coverage, or confidence levels.

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?

Two sentences, front-loaded with the action and scope, then the format mapping, then the caveat. Nothing is repeated from annotations or the schema and no sentence is 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 only two required parameters and an output schema that carries the return structure, the description covers what an agent needs to build a valid call. The remaining gap is minor: no note on what happens if the supplied document does not match the declared provider format.

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 description coverage is 0%, so the description must carry the burden, and it does: it maps the `provider` enum values to the concrete document shapes expected in `policy` (AWS policy JSON, Azure role definition, GCP IAM bindings). It stops short of describing required keys inside each format, which keeps it from a 5.

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 ('Inspect an IAM document for broad grants') and enumerates the three accepted document formats, which is enough to separate it from review siblings like cloudformation_review or terraform_plan_review. It does not explicitly name those siblings as alternatives, so it stops short of a 5.

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 default provider (AWS) and the accepted per-provider formats imply when the tool applies, and 'the provider analyzers are authoritative' hints that this is a first-pass check. However, there is no explicit statement of when to reach for this versus a deeper review tool, nor any exclusion or prerequisite.

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