Send a message

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

The description makes the primary side effect clear: it posts a message. It also surfaces the potential account risk of sending unsolicited messages, which is valuable behavioral transparency. The annotations already indicate this is not read-only and not destructive, and the description aligns with them without contradiction.

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 description is a single sentence that front-loads the core action and then adds the important usage caveat. Every word contributes meaning, with no unnecessary detail or 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?

The description covers the main intent, the distinction between replying and starting a thread, and the key risk of unsolicited messages. It does not provide examples or explicitly state that thread_id and to_profile_id should not be combined, but the 'or' phrasing and parameter descriptions are sufficient for an agent to use the tool correctly.

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?

The thread_id and to_profile_id parameters are described in the schema, clarifying that thread_id is for existing threads and to_profile_id is required for new threads. The required message parameter lacks a dedicated description, but the main tool description makes its purpose obvious. This is slightly less than full coverage but still clear.

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 name 'send_message' clearly indicates the action, and the description specifies sending a message to an existing thread or starting a new one. It is easily distinguished from sibling tools like list_threads, get_thread, and thread_action, which focus on reading or managing threads rather than sending 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?

The description explicitly explains when to reply to an existing thread versus when to open a new one, and warns against sending unsolicited messages to employers. This gives strong guidance on appropriate usage and when not to use the tool, which is especially important given the account risk mentioned.

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