Invoke agent

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

Goes beyond annotations by detailing blocking behavior, credit consumption, timeout mechanics, status values (running, awaiting_input), and the URL in results. No contradiction with annotations.

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?

Every sentence adds value: purpose, default behavior, timeouts, blocking, wait=false guidance, credits, edge cases, and URL. Front-loaded and no fluff.

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?

Covers all critical aspects: return values, states, credit cost, alternative tools, blocking nature, and human input flow. No output schema but description compensates fully.

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 baseline is 3. The description adds significant meaning for the wait parameter (usage guidance), but other parameters (agent_id, session_id) rely mostly on schema. Overall adds value beyond schema.

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 clearly states 'Send a message to an agent' and explains the default behavior and alternative outcomes, distinguishing this tool from siblings like list_runs or get_run_result.

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?

Explicitly advises when to use wait=false ('if the user is not waiting on this reply, or you expect a long turn'), references get_run_result for polling, and mentions list_pending_inputs/answer_pending_input for human input handling.

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