Send an X direct message

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

The description goes far beyond the minimal annotations. It discloses that the message cannot be taken back, that sending incurs credit costs, that X may refuse delivery based on recipient settings, and that connectivity may require a one-time reconnection. It also explains the idempotency key's role in preventing duplicate sends. This provides a complete behavioral profile for a side-effecting action, covering risks, costs, and failure modes that annotations alone do not convey.

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 dense but well-organized: it leads with the core action, then parameter-specific details, followed by a prominent safety warning, usage constraints, failure behavior, cost, and connectivity prerequisites. Every sentence adds actionable information, and the critical consent requirement is highlighted in capital letters. No fluff or redundancy; the structure is efficient and scannable.

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?

Given the tool's real-world side effects (sending a private message to a person), the description covers all essential operational context: safety (explicit consent), recipient identification nuances, idempotency for retries, credit costs, provider-side refusal, and connectivity requirements. It also references companion tool list_x_dms for obtaining IDs. Nothing an agent needs to make an informed call is missing, and the lack of an output schema is offset by clear expectations of refusal behavior.

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?

The input schema already provides rich, 100% coverage for all four parameters, including the numeric vs handle distinction for participantId and the source of conversation IDs. The description reinforces the 'one message to one recipient' rule and the idempotency key's purpose, but these largely repeat or apply what the schema already documents. Since the schema carries the heavy lifting, the description adds only marginal extra semantic value, so a baseline 3 is appropriate.

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 clearly states the action (send a direct message), the resource (from the connected X account), and the two distinct modes (existing conversation via conversationId, or to a named account via participantId). It distinguishes itself from sibling social DM tools by specifying X, and the detail about starting a new conversation makes its scope unambiguous. No ambiguity remains about what this tool does.

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 provides clear guidance on when to use each parameter (conversationId vs participantId), and gives explicit exclusions (never send the same message to multiple people, X may refuse if recipient settings don't allow). It also instructs the agent to obtain explicit user consent before calling. However, it does not explicitly contrast with alternative DM tools (e.g., send_bluesky_dm) or state conditions under which one tool should be chosen over another, leaving some inference required from the tool's own name.

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