Author Script operator

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

Annotations already convey that this is a write/creation operation (readOnly=false, destructiveHint=true). The description adds substantial context beyond that: creates companion callbacks DAT, appends custom params based on type, returns a specific dictionary, requires environment variables, and notes the non-cooking behavior when nothing requests the op. It does not explicitly mention overwrite conflicts, but the added context is valuable.

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?

Three well-organized sentences: front-loaded purpose, then mechanism, return value, prerequisites, and a practical cooking caveat. Every sentence contributes meaningful information with no filler, making it easy for an agent to parse quickly.

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?

Covers purpose, mechanism, return structure (explicitly lists keys), environment requirements, and a common behavioral pitfall. No output schema exists, so the return dict mention helps. Lacks details on what happens if an existing op has the same name (destructive potential), but overall the description is sufficiently complete for a creation tool.

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%, with each parameter already explained in detail (e.g., family selects operator type and stub signature, custom_params type inference). The description largely mirrors schema information, adding only minimal extra context such as the per-family stub names (chan/row/point/numpy). Baseline 3 is appropriate because the schema carries the semantic load.

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 uses a specific verb ('Scaffold') with a clear resource ('Script CHOP/DAT/SOP/TOP') and detailed outcome (onCook stub, custom parameters, companion callbacks DAT). It distinguishes from sibling tools like create_python_script and add_custom_parameters by its focus on the full Script op scaffolding workflow.

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?

Provides clear context: when to use it (scaffolding a Script op with optional custom parameters and stub generation). Also states critical prerequisites (TDMCP_RAW_PYTHON=on, TDMCP_BRIDGE_ALLOW_EXEC=1) and a behavioral caveat about cooking. However, it does not explicitly name alternatives or conditions where another tool should be used instead, so it misses full when-not guidance.

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