create_session

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

With no annotations at all, the description carries the full burden and does so well. It discloses return payload semantics, the hosted callback flow, the PROOF_API_KEY access requirement, and the special handling of qr_text. It even names the terminal states (verified, failed, expired) that downstream polling will encounter.

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 front-loaded with the tool's purpose and outputs, then moves into actionable agent usage, then access requirements. Every sentence adds operational value — the qr_text warning, the render_auth_link handoff, and the wait_for_session polling step are all necessary for correct invocation.

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 tool with six parameters, a nested metadata object, no output schema, and no annotations, the description is remarkably complete. It covers what the tool returns, how the returned values should be used, what to avoid, how to poll for completion, and the access setup required. An agent can call this tool correctly with minimal inference.

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 schema already documents all six parameters and their formats. The description does not add parameter-level detail beyond the schema, but it references the overall phone verification purpose and the output-driven workflow. Baseline 3 is appropriate because the schema does the heavy lifting.

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 new phone verification session' — and immediately states the concrete return values (deep_link, qr_code, qr_text). It also distinguishes itself from the large sibling set by describing the hosted verification flow and explicitly noting that start_login does NOT open this tool.

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?

It gives explicit downstream usage: pass deep_link to render_auth_link, never pass qr_text to a link renderer, print qr_text verbatim only for a real terminal, and poll with wait_for_session. It also provides a clear exclusion ('start_login does NOT open this tool') and an access prerequisite, making when and how to use the tool unambiguous.

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