Create an agent

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

All annotations are false, so the description carries the burden of behavioral disclosure. It adds valuable context by disclosing the exact error for invalid models (unsupported_model), the required scope (agents:write), and the exclusive voice-pipeline constraint. It does not mention idempotency or whether duplicate calls create duplicate agents, but the disclosed error and scope behavior go beyond what the schema and annotations provide.

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 compact and front-loaded. Every sentence serves a purpose: what the tool does, the prerequisite workflow, the key voice constraint, and the required authorization scope. There is no filler or repetition of the input schema.

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 complex tool with 8 parameters, a nested voice object, and no output schema, the description covers the most error-prone parts: model validation, voice pipeline exclusivity, and authorization. It does not describe the creation result shape or whether the agent is immediately usable, but the structured schema carries most parameter detail and the critical runtime constraints are present.

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%, so the individual parameters are already documented well. The description adds important semantic value for the nested voice parameter by explaining the composed pipeline vs. realtime-model exclusivity and reinforcing that model choices must come from list_engines. This helps an agent avoid invalid voice payloads even before opening the nested 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 opens with a specific verb and resource: 'Create a voice agent.' It clearly names the artifact being created and distinguishes this creation operation from sibling tools like update_agent, list_agents, and delete_agent. The voice pipeline detail further clarifies the specific type of agent being created.

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 gives a concrete prerequisite: call list_engines first to choose available models, and warns that unavailable or mistyped models will be rejected with unsupported_model. It also explains the voice structure choice clearly. It does not explicitly contrast with update_agent or state when not to use this tool, but for a create operation the usage context is mostly self-evident.

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