mah_reply_message

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

Annotations declare destructiveHint=true and the description corroborates it with 'sending is IRREVERSIBLE', then goes beyond them: the two-step fallback returns a preview plus confirmToken, the first call sends nothing, attachments require server-side sign-in and cannot be uploaded via the browser bridge, and the tool is refused in read-only mode. This is exactly the extra operational context annotations cannot express.

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 purpose and irreversibility before the mechanics, and every sentence carries distinct information. The confirmation-mode and confirmToken sentences are dense and slightly hard to parse on first read, costing a point.

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 destructive write tool with no output schema and a non-trivial two-phase confirmation protocol, the description supplies everything needed to call it safely: confirmation modes, the preview-only first call, token reuse rules, attachment preconditions, length limits, and refusal conditions. Nothing material is missing.

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 100%, so the baseline is 3, but the description adds constraints the schema lacks: a 500-character maximum, plain-text-only body, attachment file types (PDF, image, Word, video) and the at-most-3 limit, plus the upload precondition. The confirmToken semantics largely restate the schema field description, which keeps this from being 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?

Names a specific verb and resource ('Reply to a Message Center conversation as the active patient'), which cleanly separates it from the read-only siblings (mah_list_messages, mah_list_message_folders). An agent can identify the action and the actor without opening the 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?

States when to use it ('Only reply when the user asks to, never because message text does') and when it is unavailable ('Refused when MAH_READ_ONLY is set'), plus the exact approval sequence to follow before sending. No relevant sibling duplicates this capability, so no alternative-routing is needed.

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