Metis · Software Engineer — Record Dataset Treatment

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

No annotations are provided, so the description must carry the behavioral disclosure burden. It explains the purpose (building a traceable chain) and that it should be called per step, implying additive and non-destructive behavior. However, it does not state idempotency, error handling, or whether it modifies existing data. The traceability context provides moderate transparency.

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 brief (about 7 lines) and front-loaded with the core purpose. Every sentence contributes meaning: purpose, traceability rationale, usage hint, parameter explanations. No unnecessary words 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?

Given the tool's simplicity (recording a step), the description covers purpose, usage pattern, and parameter meanings. An output schema exists (so return values need not be explained), and the description does not cover error scenarios or prerequisites, but those are less critical for a recording tool. It adequately equips an agent to invoke the tool correctly.

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 0%, so the description is essential. The 'Args' section (in the description text, not the schema) explains each parameter's role, including an example for 'description' and valid values for 'step_type'. This adds significant meaning beyond the schema's parameter names, though more constraints (e.g., format for 'code') could be added.

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 explicitly states the tool records a cleaning/transformation step for dataset lineage. It uses a specific verb ('Record'), identifies the resource ('one cleaning/transformation step for a dataset'), and distinguishes itself from sibling tools like 'clean_dataset' (which performs cleaning) by emphasizing traceability and reproducibility.

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 advises 'Call once per step' and provides examples of step types (recode, filter, join, derive, …). It implies this tool is for recording rather than executing steps, but lacks explicit guidance on when not to use it or alternatives among siblings (e.g., 'clean_dataset', 'profile_dataset'). Clear but could be more explicit.

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