rehearse_call

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

With no annotations, the description carries the full burden and does well: it discloses that the real agent runs with the real briefing, that the mode is text, and that nobody is actually called — important safety-relevant context. It omits lifecycle details such as how the rehearsal ends (end_rehearsal) or whether state persists.

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-loads the core action in the first clause, then gives the operational workflow. Dense but each sentence earns its place; the parenthetical about events_after is slightly compressed but functional.

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?

An output schema exists and the description explains how to consume its events, so return values need not be restated. It covers start-of-rehearsal and the interaction loop, but not how the rehearsal concludes, which an agent must learn from end_rehearsal.

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 0% and call_id has no schema description, but the description's framing ('a drafted call') makes the parameter's role inferable as the id of the drafted call. With a single trivial parameter, this is adequate but adds no explicit format or sourcing detail.

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 and resource ('Start a rehearsal of a drafted call') and immediately scopes it as text-only with no real call placed. This clearly separates it from siblings like confirm_call (real call) and rehearse_say (mid-rehearsal reply).

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?

Explicitly routes the agent to the follow-up tools: read agent output with wait_for_event (passing returned events_after as after) and reply with rehearse_say. It stops short of stating when to rehearse instead of placing a real call (e.g., before confirm_call), so it is clear context but not full when/when-not guidance.

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