agents_invoke_agent

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It does reveal key side effects: it creates a new conversation thread (rather than continuing an existing one) and performs is asynchronous by returning an ID rather than a result. However, it does not mention potential side effects, whether the invocation is blocking or fire-and-forget beyond the ID pattern, or any auth/rate-limit constraints. The behavioral descriptions given are accurate and useful but somewhat minimal.

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 two concise sentences, front-loaded with the primary action and immediately clarifying the return artifact. Every sentence earns its place, though the lifecycle info about thread creation and ID return is packed compactly. No wasted words, though the 'optional context' phrase slightly duplicates the parameter description.

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 this is an asynchronous invocation tool with an output schema and well-documented parameters, the description is reasonably complete. It explains the async pattern (returns ID, use status/result tools), which is essential operational knowledge. It could add a bit more about the relationship between the file_context param and typical agent usage, but for a tool whose complexity is moderate and whose lifecycle is clearly mapped to siblings, this is adequate.

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 already has 100% coverage with descriptions for all 3 parameters, so the baseline is 3. The description adds value by clarifying that the returned invocation ID pairs with specific sibling tools for status polling and result retrieval, which helps the agent understand how the output parameter relates to the workflow. It also indicates that task is the required payload while file_context is optional supplementary context. This adds meaningful orchestration context beyond the raw 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 the verb ('Invoke an agent or workflow'), the resource ('with a task and optional context'), and outlines the specific lifecycle: creates a new thread, submits the task, and returns an invocation ID. It also distinguishes itself by pointing to sibling tools (agents_get_invocation_status and agents_get_invocation_result) for following up, which clarifies its role as the initiation step in the workflow.

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 implicitly conveys when this tool is appropriate: to start an agent invocation and obtain an ID for later polling. It names the status and result retrieval tools as the follow-up path, providing clear context on the lifecycle. However, it does not explicitly state when NOT to use this tool (e.g., when you just want to list agents) or name agents_list_agents as a prerequisite-alternative.

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