Send a Direct message

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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false). The description adds real value on top: the messaging-window constraint, the Human Agent feature prerequisite, the payload size cap, and the confirmation-before-send requirement. It does not describe failure behavior when the window is exceeded or what a successful send returns, which is the main remaining gap for a send tool with no output schema.

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, front-loaded with the core action, then the eligibility constraint, then the size limit and confirmation note. No sentence is filler and nothing is buried mid-paragraph.

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 5-param send tool with no output schema, the description covers the action, the hard eligibility window, the size cap, and the confirmation gate, which is what an agent needs to call it correctly. Residual gaps are error/return behavior, which are secondary against a well-documented schema.

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 80%, so baseline is 3, and the description earns the bump by clarifying two params beyond the schema: the message cap is stated in bytes while the schema's maxLength is in characters, and the 7-day window is explicitly tied to the human_agent flag. The recipient_id and confirmation_token details are left to the schema, which already documents them.

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: 'Reply in Instagram Direct to someone who messaged this account.' That wording also scopes it to replies within an existing thread rather than initiating conversations, which separates it in spirit from list_conversations/get_conversation siblings, though it never names an alternative tool explicitly.

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 concrete eligibility rules: only within 24 hours of the recipient's last message, extended to 7 days when human_agent is used and the Meta app has that feature. It also notes the user-confirmation requirement. It stops short of naming sibling tools such as private_reply as the alternative path when the 24h window is closed.

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