create_direct_message

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

Annotations do not indicate idempotency, but the description does, adding valuable behavioral context. It also discloses the return of 'created: true/false'. No contradictions with annotations. The description covers important behavioral traits beyond what annotations provide.

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 very concise: two sentences that front-load the purpose and idempotency. Every sentence adds value without unnecessary words. Structure is clear and easy to read.

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 has a single parameter with comprehensive schema coverage, an output schema (implied by return values), and clear behavioral description including idempotency, the description is fully adequate for an AI agent to understand and invoke the tool correctly.

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 describes the 'person' parameter, but the description adds meaningful context: it accepts email or exact display name with an example (Smith,Bill). This enriches understanding beyond the schema's generic description, even though coverage is 100%.

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 tool opens a one-to-one DM with a workspace member, specifying verb and resource. It distinguishes from sibling tools like 'create_group_direct_message' and 'send_dm_message' by mentioning that the returned ID is used for sending messages, and the idempotent behavior sets it apart.

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 explains when to use the tool (opening a DM with a member) and the idempotent behavior (returns existing if already exists). It implicitly differentiates from alternatives like group DMs or sending messages. However, it does not explicitly state when not to use it or provide direct comparisons to siblings.

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