Invoke agent

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

Beyond annotations (openWorldHint=true, destructiveHint=false), the description discloses many behavioral traits: it blocks the caller's turn, waits up to ~25s, may return a running status with run_id, bills credits, enforces in-flight caps (429), does not queue turns, handles human-input pauses with awaiting_input, and returns a session URL. There is 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?

Though long, every sentence earns its place. The description front-loads the purpose and then systematically covers usage rules, blocking behavior, billing, retries, human input, and result contents. No redundancy or filler; the density is justified by the tool's complexity.

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?

No output schema exists, so the description carries full responsibility for return values—it explains the reply, run_id with status 'running', awaiting_input details, and a URL. It also covers error conditions (429), side effects (credits, billing), and integration with sibling tools (poll via get_run_result, respond via answer_pending_input). For a tool with 7 params and complex async behavior, this is complete.

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 schema has 100% coverage for all 7 parameters, so the baseline is 3. The description adds meaningful context for wait (explains blocking and no backgrounding, when to switch to wait=false), idempotency_key (retry scenario and billing avoidance), and session_id (carried from previous results). This extra guidance raises the score above baseline.

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 opens with a specific verb+resource: 'Send a message to an agent and get its reply,' which clearly defines the tool's core purpose. It also distinguishes from sibling tools by explicitly mentioning get_run_result and answer_pending_input as related operations, and contrasts invoke_agent with 'a plain code sandbox' for stateless work.

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?

Provides explicit when-to-use guidance ('work that should outlive a single request'), when-not-to-use ('stateless snippet... plain code sandbox is cheaper'), and when to set wait=false for long turns. Also explains when to use idempotency_key for retries and references get_run_result and answer_pending_input for follow-up, giving clear alternatives.

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