diagnose_iam_exposure

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

Annotations only declare readOnlyHint=true, and the description adds real context: the [READ][risk=low] tag, the group-policy resolution behavior, worst-first ranking, and the critical disclosure that MinIO denies by default so NO_EFFECTIVE_POLICY accounts are silently broken. It stops short of describing envelope shape or cost, but the behavioral value added is substantial.

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 read/risk tag and one-line summary, then the substantive detail. The finding list is dense but each category earns its place by telling the agent what can be returned. Slightly verbose in the parenthetical explanation, but no wasted sentences.

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?

For a two-parameter read-only diagnostic with no output schema, the description covers purpose, ranking semantics, finding taxonomy, and both parameters. An agent has enough to call it correctly; only the envelope structure and pagination details are unstated.

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 parameter meaning, and it does: limit is the maximum findings returned and truncation is reported in the envelope, while target is the MinIO target name from config with an explicit omit-for-default rule. Both of the two parameters are explained beyond their bare titles.

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 (diagnose IAM exposure) and enumerates the concrete finding categories returned (NO_EFFECTIVE_POLICY, FULL_ADMIN_POLICY, BROAD_DATA_POLICY, DISABLED_BUT_PRIVILEGED). This clearly distinguishes it from sibling listing tools like iam_users and iam_policies, which enumerate rather than diagnose.

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 implies its value proposition (it resolves group-inherited policies so correctly-managed users aren't misreported), which hints at when it beats a raw user listing. However, it never explicitly states when to choose this over iam_users, iam_policies, or bucket_exposure_audit, nor does it state exclusions. Usage is implied, not prescribed.

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