send_message

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

With no annotations provided, the description carries the behavioral disclosure burden. It reveals auth requirements, the IGSID recipient requirement, and the limitation around paid message tags. It does not discuss result behavior or side effects, but the output schema can cover return shape.

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 description is short, front-loaded with the action, and every sentence adds value: the action, the requirements, the ID definition, and the limitation. There is no filler or repetition of schema fields.

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 send-DM tool with an output schema, the description covers the core constraints and the key non-obvious parameter. It could mention how the optional account field is resolved, but overall it gives an agent enough to invoke the tool correctly within its documented context.

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 0%, so the description must explain parameters. It usefully defines recipient_id as an IGSID and clarifies a potentially confusing prerequisite, but it does not explain the 'account' parameter or any constraints on 'text'. The description partially compensates but not fully.

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?

The description opens with 'Send a DM,' which clearly names the verb and resource. It is distinct from sibling tools that list messages or publish media, though it does not explicitly name a differentiating sibling for sending DMs versus replying to comments.

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 gives explicit prerequisites: Meta App Review and the 24-hour standard-messaging window. It also states when not to use it by noting that paid message tags outside the window are not handled here, though it does not name an alternative tool.

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