React to message

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

Annotations only declare the read/write and idempotency profile; the description adds the real behavior an agent needs — dry-run gating tied to plan_id, and a local refusal when the 24-hour messaging window is closed, which is a precondition not derivable from any annotation. It also characterizes the call as a reaction acknowledgement rather than a message send.

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 primary action is front-loaded and every clause carries operational weight (emoji choice, removal, dry run, plan_id, window check, id provenance). It is compressed into a single long sentence with em-dashes and semicolons, which costs some scannability versus shorter separate lines.

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 an 8-parameter write tool with no output schema, the description covers the mutation semantics, the gating flow, the preconditions, and what a dry run produces. The main remaining gap is that it never states what happens if reaction is omitted without remove:true, nor characterizes the success response shape.

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%, so the baseline is 3; the description earns one more by tying parameters into a workflow the schema states only per-field: apply must carry the plan_id of a preview, and conversation_id is preferred because it enables the window check. It also flags where message_id comes from, though most individual parameter meaning is still left to the schema.

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 ('React to ONE Messenger message as the Page with a single emoji') and covers the inverse operation ('remove the Page's reaction with remove:true'). The 'one message, single emoji, as the Page' scoping plus 'acknowledgement without a text reply' clearly separates it from facebook_send_message and facebook_like_comment.

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: dry run by default, apply:true requires a plan_id from a preview, pass conversation_id so the recipient and 24-hour window are validated first, and take message_id from facebook_get_conversation. It stops short of explicitly naming siblings it should not replace (e.g. facebook_send_message for text replies), so the routing guidance is implied rather than enumerated.

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