Sigma Run Workbook Agent

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

Annotations already mark this as non-read-only, but the description adds valuable behavioral context beyond that: it is a mutating/execution operation, consumes LLM tokens, and requires explicit confirmation. This is exactly the kind of side-effect information an agent needs before invoking. It does not mention async behavior or output side effects, but the provided context is meaningful.

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 compact and front-loaded: a one-line purpose statement followed by short, high-signal bullet lines. Every sentence earns its place, and nothing is wasted restating the tool name or schema. It is easy to scan and immediately actionable.

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 output schema covers return values, so that omission is fine. But the operation is complex, with 9 parameters and zero schema-level descriptions, and only messages and version_tag_name receive semantic explanation. There is no guidance on max_turns, max_output_tokens, response_format, or the relationship between the schema default confirm=false and the prose requirement confirm=true. The tool is callable, but the description is not fully complete for such a non-trivial operation.

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%, so the description must compensate. It does usefully document messages (list of conversation turns with roles) and version_tag_name (defaults to latest published version). However, 7 of 9 parameters such as metadata, max_turns, response_format, and max_output_tokens have no description beyond their names and defaults, leaving some semantics to inference. Partial compensation, but with clear gaps.

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: 'Run an in-workbook AI agent with conversation messages.' This clearly distinguishes execution from the sibling listing tools such as sigma_list_workbook_agents and sigma_list_org_workbook_agents. An agent can tell exactly what operation this performs without opening the schema.

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 explicitly frames this as a 'Mutating / execution operation,' notes that it consumes LLM tokens, and requires confirm=True. It also explains the messages input and version_tag_name default. It does not explicitly name alternative tools or give a broad 'when not to use' statement, so it stops short of a 5.

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