react_to_message

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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=true, openWorldHint=true), and the description still adds substantive behavior: the one-reaction-per-message rule, replace-vs-no-op semantics for repeated emoji, remove=true retraction with emoji still required, and that the change hits Signal's servers rather than local storage. It even names the return payload, which no output schema provides.

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?

Front-loads the action and its purpose in the first clause, then layers targeting, semantics, and return value in a tight sequence. It is dense and semicolon-heavy, but every sentence carries distinct information rather than repetition.

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 six-parameter mutation with no output schema, the description covers sourcing the target identifiers, the mutual-exclusivity of recipient/group_id, replacement and retraction semantics, and the return shape. Nothing an agent needs to call 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%, so the baseline is 3, but the description goes further: it specifies target_author as the sender's E.164, explains that target_timestamp is a millisecond value obtainable from get_conversation or a send_* result, and clarifies the recipient/group_id pairing and the default of remove. Only minor gaps remain (no note on timestamp unit edge cases).

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 precise verb+resource ('Add or remove your emoji reaction on a message') and scopes it to DMs or groups. It explicitly contrasts itself with the sibling text-reply tools (send_message / send_group_message), so an agent can route correctly without opening a 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 an explicit when-to-use ('to acknowledge without replying') and names the alternatives for the other case. It also states the routing rule between the two targeting modes ('Give recipient for a DM or group_id for a group; neither is an error'), leaving nothing to inference.

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