attach_user_policy

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

Beyond the annotations, it discloses the risk tier, the reversibility path, and an unusual safety caveat: canned policies replace rather than add, so the call can silently narrow the tool's own credential and is refused in that case. That is exactly the kind of non-obvious behavior annotations cannot express (destructiveHint=true alone doesn't convey replace-semantics or the self-refusal).

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 [WRITE][risk=medium] and the reversibility note, followed by the single most important behavioral caveat, then a compact Args list. No sentence is redundant given the zero schema coverage.

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?

Covers safety, reversibility, and every parameter despite no output schema and thin annotations. The one gap is that it doesn't clarify what happens to policies already attached to the user (the replace-semantics note is framed around the tool's own credential, not the target user).

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 carries the full burden — and it documents all four parameters, including provenance hints (access_key from iam_users, policies from iam_policies), the default behavior of omitting target, and the semantics of dry_run as a preview.

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 ("Attach canned policies to a user") and immediately names the inverse sibling operation ("Reversible → detach"), which is enough to distinguish it from detach_user_policy and the other iam_* tools without opening a 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?

Gives a clear context cue (attach vs. the detach alternative) and mentions dry_run as a preview path, plus the credential self-refusal case. It does not spell out when-not to use this versus siblings like create_user or set_user_status, so it stops short of full when/when-not guidance.

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