send_message

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does disclose the operation is a mutating send on an existing thread, which implies it won't create a thread. But it doesn't mention failure conditions (e.g., invalid thread_id), delivery semantics, permissions, or attachment behavior beyond what the schema already states.

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?

A single sentence with verb, resource, and constraint, front-loaded with the verb 'send.' There is no filler and every word earns its place. Slightly more could be added given the absence of annotations, but as a structure it is appropriately sized.

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 moderate-complexity tool with fully described parameters and an output schema, the description covers the core what. Missing are usage routing against message-management siblings like mark_message_handled, and any failure-context hints. Since no annotations exist, the description is adequate but not genuinely enriching.

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 description coverage is 100% — body, thread_id, and attachment_url each have descriptive text, including how to learn the thread ID and the ~5MB attachment cap. The description adds no meaning beyond the schema beyond characterizing the recipient as a guest, so the baseline 3 applies with the schema doing the heavy lifting.

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 ('Send a message') plus the context ('to a guest on an existing conversation thread'). This clearly distinguishes the action from read-oriented siblings like list_messages and get_message_event. However, it never names an alternative explicitly, so the differentiation is implicit rather than stated.

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 phrase 'existing conversation thread' implies the tool requires a pre-existing thread and will not create one, which is a meaningful usage constraint. But the description gives no explicit when-to-use/when-not-to-use guidance or alternatives, and the prerequisite on how to obtain thread_id lives in the schema, not the description. Usage is implied, not spelled out.

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