fit_mmm

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

With no annotations, the description must carry the burden of behavioral disclosure. It only adds the constraint 'No arbitrary Python is accepted' and lists supported types, but does not mention side effects (e.g., whether a model is overwritten), compute time, return value behavior, or failure modes. This is a significant gap for a fitting operation.

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 with the main purpose. The listing of types is fairly long but directly relevant to configuration. It avoids redundant filler, though some enum lists duplicate schema information.

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 complex tool with a nested config object and no output schema, the description is too high-level. It does not explain return values, synchronous/asynchronous behavior, prerequisites (like registered dataset), or consequences of fitting. The schema covers parameter syntax, but the description leaves key operational context unaddressed.

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% in the textual description, but the input schema itself has rich descriptions for nested parameters (e.g., dataset_id, date_column, AdstockConfig). The description adds the 'No arbitrary Python' constraint and summarizes the type enums, which is marginal value beyond the schema. Since the schema already carries parameter explanations, a baseline of 3 is appropriate.

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 states a specific verb ('Fit') and resource ('Bayesian Marketing Mix Model'), and clearly differentiates itself with 'No arbitrary Python is accepted' – signaling this is a controlled-config tool rather than a code execution tool. It also names the supported adstock and saturation types, which helps distinguish it from prediction/analysis 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?

No guidance is given on when to use this tool versus alternatives like submit_fit_mmm_job (likely async) or other model-fitting tools. It does not mention prerequisites such as the dataset being registered, nor does it state that this is a blocking operation.

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