createSession

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

Goes beyond annotations by disclosing that the Session does not start audio on its own, returns a single-use expiring ws_url, and that the API key must never reach the browser. These are important behavioral traits not captured in the annotations (readOnlyHint=false, destructiveHint=false) and add significant value.

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 structured with a clear first paragraph stating purpose and behavior, and a second paragraph for usage/security. Every sentence contributes, but the 'see below' pointer and tag add slight verbosity. Still efficient and 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 complexity (nested requestBody, no output schema, minimal annotations), the description is complete: it explains the two-step process, the ws_url return value, server-side invocation, client handoff, and security implications of the session. No important context is missing.

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 input schema already has 100% coverage with descriptions for agent_id, type, and custom_variables. The description does not add new parameter-specific semantics, so the baseline of 3 applies per the rubric for high schema coverage.

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 'Create a voice Session' and elaborates with a specific definition: 'a short-lived, single-conversation reservation that lets a client hold a live voice chat with your agent.' This distinguishes it from sibling tools like createAgent or createBulkCall by focusing on the session-specific purpose.

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 guidance: 'This is step 1 of 2', explains that creating does not start audio, and instructs to call from server with API key, returning only ws_url to the client. It also clarifies when not to give the API key to the browser, offering clear when-to-use and security context.

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