iam_desktop_reply

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

With no annotations present, the description carries the full burden and delivers: immutability ('One immutable reply per request'), idempotency ('identical retries are safe'), and attachment semantics ('copied, not live path links', per-file and per-category size caps, UTF-8 requirement). These are exactly the behavioral facts an agent needs before invoking a mutation.

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 purpose and the ONLY constraint are front-loaded, and each subsequent sentence adds a distinct constraint (attachment limits, copy semantics, safety exclusions, idempotency). It is dense but no sentence is filler; a light break into separate clauses would aid scanning.

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?

An output schema exists, so return values need not be described, and the mutation's safety profile is well covered despite missing annotations. The only material gap is the role/format of request_id and the optional mailbox, which an agent must infer.

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 compensate, and it does for the non-obvious parameters: image_paths and file_paths get formats, counts, and size limits, and body is tied to 'Include a caption' / UTF-8 text. request_id and mailbox receive no explanation, leaving a partial gap.

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: 'Publish an intentional reply ... to a human IAM Desktop request addressed to your mailbox.' This cleanly separates it from the email siblings (iam_reply, iam_send) and from notify-style tools by naming the request/reply model.

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 'ONLY to a human IAM Desktop request' constraint and the 'Never forward unrelated mail, private notes, reasoning, secrets or tool output' exclusion give clear when/when-not guidance. It stops short of naming the alternative sibling (e.g. iam_reply) for non-desktop cases, so it is strong but not fully routing.

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