Send a direct message (opt-in only)

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

The description adds significant behavioral context beyond annotations: the opt-in enforcement mechanism, cost per event, fixed cost, throttle rate, and force bypass with human approval. No contradiction with the provided annotations.

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?

Three tight sentences deliver essential information without fluff. Each sentence adds value: the core rule, the force exception, and pricing/limits. Front-loaded with the action.

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?

Core behavior and safety constraints are well covered, but with five parameters and no output schema, critical details like identifying the recipient and the meaning of 'reason' are underexplained. The description is adequate but not fully complete.

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 only 20% (force only). The description adds throttle/cost info but does not explain how to specify the recipient (user_id vs username), the required 'text' parameter, or the optional 'reason' parameter, leaving a substantial 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?

The description clearly states the action ('Send a DM') and the resource (direct message). It distinguishes from siblings like 'inbox' and 'reply' by highlighting the opt-in-only constraint and the explicit focus on direct messages.

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?

Provides concrete guidance on when the tool is allowed (only after the recipient DM'd you first) and explains the force bypass. However, it does not explicitly mention alternatives or when to prefer this over sibling tools like 'reply'.

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