Send message

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

Annotations already declare destructiveHint=true, non-idempotent and open-world, and the description is consistent, reinforcing irreversibility with 'A sent message cannot be recalled'. It adds genuinely non-annotated behavior: messages are sent under your name, and non-followers receive the message as a request. It omits rate limits and failure modes for invalid handles.

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?

Four short sentences, front-loaded with the action, then targeting, then the delivery caveat, ending on the destructive warning. No sentence is disposable.

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 mutation tool with no output schema, the description covers targeting, delivery semantics and irreversibility, which is most of what an agent needs. It does not indicate what the call returns (e.g. a message or conversation identifier), leaving a minor gap.

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 baseline would be 3, but the description adds real meaning beyond the schema: the mutual-exclusivity constraint ('Give one of conversation_id or user') and what the `user` path does behaviorally (reuses an existing conversation or creates one, and becomes a message request if the person does not follow you).

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 ('Send a direct message on Substack') plus the two targeting modes (conversation vs person) and the nature of the channel ('private chat message'), which implicitly separates it from the public reply_to_comment / reply_to_note siblings. An agent can tell what this does 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?

'With conversation_id it replies there; with user it writes to that person' plus 'Give one of conversation_id or user' clearly routes the agent between the two invocation modes. It stops short of naming alternatives or stating when not to use this tool (e.g. public reply vs private DM), so it is clear context without explicit exclusions.

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