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

Annotations already mark this as a non-readOnly, open-world, destructive operation; the description adds value beyond them by disclosing the failure mode (policy rejection, 24h/template constraints) and a human-confirmation gate. It still doesn't say what the call returns or whether a partially sent message can be retracted.

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 short sentences ordered by importance: what it does, how it fails, and the confirmation requirement. No filler, no restatement of the title, and the failure caveat is placed before the action guidance where it matters most.

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 write tool with no output schema, the description covers purpose, the policy risk, and a safety gate, which is enough to call it correctly. It stops short of describing the response or rate-limit behavior, which would be the remaining useful additions.

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 75% and the schema itself fully explains the tricky idempotencyKey retry contract; the description adds no meaning about username, accountId, or message content. At this coverage level the baseline of 3 is appropriate, since the description neither compensates for nor undermines the documented params.

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: 'Open a direct message with someone who has not written first.' The phrase 'has not written first' implicitly separates it from send_message/reply flows in existing threads, though no sibling is named explicitly. An agent can tell what the tool 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?

Gives clear operating conditions: networks restrict unsolicited DMs to a 24h window or approved template, so policy failure is expected, and for public-facing use the agent should confirm with the user first. It does not name send_message as the alternative for replying in an existing thread, leaving that inference to the reader.

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