build_master_dark

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

The description discloses behavior beyond the annotations: it is 'Cached by fingerprint' and 'Async: returns job_id.' These are genuinely useful execution traits that the annotations do not convey. It stops short of detailing whether cached results bypass processing or what failure modes exist, but it adds meaningful context.

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?

Four short sentences, each earning its place: the core action, a critical parameter warning, a caching note, and the async interface. Information is front-loaded, with the primary purpose first and the most important caveat second. 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?

The description covers the essential execution model (async, job_id, caching) and one critical parameter, but it does not fully compensate for the missing schema descriptions of wait, force, and rejection. With six parameters and no output schema, an agent may still be uncertain about how to request synchronous execution or control rejection behavior.

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 only 33%, so the description carries a heavier responsibility. It does add value for master_bias by stating when it should not be passed and why. However, parameters like wait, force, and rejection remain undocumented in both the schema and the description, leaving the agent to infer their meaning.

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: 'Integrate darks into a master dark.' It clearly identifies what the tool does and is easily distinguished from sibling tools like build_master_bias and build_master_flat by the resource it produces (a dark master) and the input it integrates.

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 clear operational guidance: it explicitly warns not to pass master_bias unless using dark optimisation, explaining the CMOS rule that 'bias lives inside the dark.' It does not explicitly compare to sibling build tools, but the rule is a strong usage constraint that helps an agent decide when and how to invoke this tool.

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