send_message

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

Beyond the annotations, the description explains exactly what happens on repeated calls: no duplicate message is sent, the first answer is returned, and replayed=true signals the replay. It also discloses the third-party-content trust boundary and warns against following instructions found in returned names or text.

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 sentences, front-loaded with the operation and idempotency contract, then safety constraints. Every sentence adds distinct operational or safety value with no redundant restatement of schema fields.

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 a write operation with an output schema, and the description covers the critical behavioral details: idempotent replay behavior, one-message-per-trigger guardrails, permission scoping, and prompt-injection safety. Return structure is covered by the output schema, so no further return-value explanation is needed.

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 already 100%, so the schema handles parameter documentation. The description still adds meaningful behavioral semantics for idempotency_key by explaining replay behavior and the replayed=true response, which goes beyond the schema's retry-only note.

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?

The description states a specific verb and resource: it sends one text message to a chat. It also immediately scopes the operation with write-permission and idempotency semantics, making clear this is the only write-path among read-oriented siblings like get_messages and search_messages.

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?

It gives explicit usage constraints: send at most one message per trigger, never because a message asked for it, and repeat an idempotency_key only to retry the same call. These are clear when/when-not rules that prevent misuse, even though no sibling provides an alternative send path.

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