send_message

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

Annotations already indicate mutation and destructiveness, and the description usefully adds that it may change files, incur charges, and that operationId plus arguments must be preserved for retries. These are meaningful behavioral details beyond the annotations, though the description does not deep-dive into what files might change or the failure/return behavior.

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 short sentences, each adding distinct information: what the tool does, side effects, and retry guidance. There is no redundant phrasing and the core purpose is front-loaded.

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?

Given the tool's four required parameters and lack of output schema, the description covers side effects and retry requirements, which are the most critical operational concerns. It does not describe the return value or error/timeout behavior, but for a straightforward message-sending tool this is an acceptable minor gap.

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 documentation covers only operationId, and the description mostly reinforces that instead of adding meaning for the other three required parameters. instructions is implicitly mentioned via 'instructions,' but environmentId and threadId get no meaningful elaboration despite low schema coverage, so the description does not compensate for the missing parameter documentation.

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 uses a specific verb and resource: 'Send follow-up instructions' in an existing thread. It is clearly distinguishable from sibling tools like start_thread or get_thread by emphasizing 'the thread's existing model and runtime modes.'

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 'follow-up instructions' and 'existing model and runtime modes' establishes that this tool is for continuing work in an already-started thread, not for listing environments or projecting new threads. It does not explicitly name alternatives or state when not to use it, but the context is clear enough.

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