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

Annotations already indicate readOnly=false and openWorldHint=true, and the description adds meaningful behavioral detail: replies are sent through the original channel and routing metadata is persisted on the conversation. This goes beyond the structured fields and is consistent with the annotations, though it does not discuss errors, rate limits, or response behavior.

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 short sentences, each contributes distinct information: the core action, channel behavior, routing requirement/persistence, and an AI-drafting alternative. No filler or redundancy, though it could be slightly more compact.

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?

The tool is moderately complex with a nested routing object and no output schema. The description covers the main action, channel behavior, routing prerequisite, and an alternative for drafting. It omits return values or failure modes, but with the parameter schema fully covering inputs, the description is adequate for use.

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% and the schema already describes all parameters, including the nested routing object with persistence semantics. The description adds some value by explaining why routing is needed and that it is stored for future replies, but this largely echoes the schema's existing documentation.

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?

Description opens with 'Send a reply in a conversation' — a specific action on a clear resource. It further distinguishes the tool by noting replies go through the original channel (e.g., Instagram, X, Facebook), which sets it apart from generic messaging. However, it does not explicitly contrast siblings like reply_to_comment or draft_reply.

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?

States a clear prerequisite ('Replies require conversation reply routing metadata') and explains how to handle it ('Provide routing once and it will be stored on the conversation for future replies'). It also points to the Inbox Reply agent as an explicit alternative for AI-drafted replies with brand voice. Absence of 'do not use' wording is a minor gap, but the context is clear.

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