Run the interview (text-only in this build)

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

With no annotations, the description carries the full burden and does so: it discloses the approval gate and its refusal behavior, the AI-disclosure and recording-permission checks performed at the top of the call, that the transcript is saved, that transcripts are append-only, and that no phone call is placed. These are exactly the mutation/authorization semantics an agent needs before invoking.

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?

Front-loaded with the core action, then the refusal gate, then side effects, then the next step. Every sentence adds a distinct fact; there is no filler or repetition.

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 no annotations and no output schema, the description covers preconditions, side effects, persistence semantics, and the follow-up tool. It stops short of describing what the call returns (e.g. confirmation shape or transcript handle), which is the only remaining gap.

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%, and the schema already documents fixture/turns mutual exclusivity and that brief_id must have a matching approve_contact record. The description restates the fixture-or-turns choice and the approval gate without adding new syntax or format detail, so baseline 3 is correct.

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?

States a specific verb+resource ("Runs the interview step of the spine on text") and immediately narrows the input modes to a named fixture transcript or inline turns. It also distinguishes itself from place_call by declaring "No phone call is placed in this build," so an agent can tell it apart from the dialing sibling without opening a schema.

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?

Gives a hard precondition (refuses unless a human approval for this brief's exact person and number is on file) and names the next step (generate_piece), which is strong routing guidance. It does not explicitly say when to prefer this over place_call or fetch_transcript, so it falls just short of full when/when-not/alternatives coverage.

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