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

Goes well beyond the annotations: immediate delivery, irreversibility ("cannot be unsent"), a confirmation requirement, text-only constraint, per-platform character limits, and the 24-hour eligibility window. Annotations only give readOnlyHint=false/openWorldHint=true; the description supplies the operational risks an agent actually needs.

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?

Four sentences, each carrying a distinct decision-relevant fact (what/irreversibility, format, limits, eligibility), with the risk warning front-loaded before the constraints. No filler or restatement of the name.

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 two-parameter, no-output-schema write tool, all call-critical information is present: preconditions, irreversibility, format and length rules, and the source of conversationId. Nothing an agent needs to invoke this correctly is missing.

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 100% (baseline 3), and the description adds real value on top by giving concrete length limits (Instagram 1000, Facebook 2000) and the "Text only" type constraint that the schema's generic "Must fit the platform's length limit" leaves unspecified. It says nothing about conversationId beyond the schema's own pointer to list_conversations.

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 ("Send a direct message reply") on a specific resource (Instagram/Facebook conversation), and the "direct message" qualifier cleanly separates it from the sibling reply_to_comment. An agent can identify the tool 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 a strong gating precondition ("Only works while replyWindow.canReply is true (within 24 hours of the customer's last message)") and a procedural instruction ("confirm the wording with the user first"). It never explicitly names reply_to_comment as the alternative for non-DM cases, so routing between the two reply tools is left slightly to inference.

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