run_operation

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

With zero annotations, the description carries the full burden and delivers: return behavior (file result written to output_path or temp file, returned with size and content type; data result as JSON), cost model ($0.01 flat, failed calls free), data handling (processed in Germany, deleted after delivery), and a verification claim. This is unusually rich behavioral disclosure for a tool with no annotation support.

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?

About 150 words for a generic dispatcher with 5 params, no annotations, and no output schema — every sentence earns its place by covering purpose, op sourcing, file handling, output behavior, cost, sibling relationship, and data residency. Front-loaded with purpose and examples. Slightly long, and the closing 'published proof' sentence is marginally promotional, but nothing is wasted.

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 high-complexity generic executor with no output schema and no annotations, this description is remarkably complete: it explains what the tool does, how to source the op name, how uploads are referenced, what happens when output_path is omitted, what the return payloads look like for both file and data results, cost/failure policy, and the relationship to sibling tools. The only unaddressed area is explicit auth prerequisites, which the get_access sibling implies.

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 coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema: 'Uploads are local file paths' clarifies the files parameter, 'written to output_path, or to a temporary file when you omit it' explains output_path's optional behavior, and the examples ('pdf/merge', 'ocr', 'text/chunk') illustrate the op naming convention. Slightly above baseline, but it doesn't exhaustively define params semantics.

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 ('Run any bigapi operation on real files') backed by concrete examples (merge/redact PDF, OCR, convert image, chunk text, read ZUGFeRD invoice). It distinguishes itself from siblings explicitly: 'This one executor covers every operation... enable_tools only adds convenience wrappers around it,' and routes op-name sourcing to find_tool. An agent cannot confuse this with the discovery or wrapper siblings.

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 explicit workflow guidance: 'Take the operation name from find_tool' tells the agent where the op parameter comes from, and 'enable_tools only adds convenience wrappers around it' is an explicit when-not-to-use-alternative statement establishing run_operation as the universal executor. Pricing and failure-cost statements further clarify when calls are safe to make. No decision is left to inference.

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