cassette_run_job

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly explains that the call blocks by acting as the wait, streams progress, returns terminal envelopes, and can be detached via wait=false. It also discloses the review_required branch and the required follow-up action, though it does not describe side effects, authentication, or asset mutation.

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 long but information-dense, with the core purpose and blocking behavior front-loaded. Nearly every sentence adds operational value, though some repetition exists around not starting additional runs and not asking for redundant confirmation.

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?

The operational flow is thoroughly explained for the main user-turn lifecycle, and an output schema exists so return-value documentation is not required. However, with no annotations and 17 undocumented parameters, the description is not fully complete for all calling scenarios, especially around the many model, session, and instruction-related parameters.

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% across 17 parameters, yet the description only meaningfully explains message, wait, and export-related behavior. Most parameters, including instruction, prompt, chat_message, cassette_message, selectors, session_id, and cassette_model, are left entirely unexplained, which is a large gap for a zero-coverage 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 states a specific verb and resource: it runs one Cassette edit turn and returns when the result is settled. It also differentiates itself from siblings by naming cassette_job_status and cassette_review_completion, and clearly defines the tool as the waiting call itself.

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 unusually explicit usage rules: exactly one call per user turn, never start follow-up runs, do not poll job_status after a settled result, and use wait=false only to detach into the background. It also names the alternative tool for resuming interrupted jobs and the review completion tool for review_required results.

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