evaluate_prior_sensitivity

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

There are no annotations, so the description carries the behavioral burden. It does explain that the tool evaluates sensitivity under alternative priors, which implies a read-only diagnostic analysis, but it does not disclose the output format, side effects, or whether it refits models. The behavioral intent is clear but incomplete.

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 a single, front-loaded sentence with no filler or redundancy. It packs the key resource, the exact quantities of interest, and the condition being varied into a compact and readable form.

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 one-parameter tool, the description provides enough to understand the core purpose and the sensitivity dimensions being examined. However, without an output schema or annotations, it should ideally say what kind of result is returned (e.g., summary tables, plots, metrics) and whether any fitted model prerequisite applies. The missing return-value clarity prevents a higher score.

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?

The only parameter, model_id, is already described in the schema as 'Model ID to evaluate for prior sensitivity'. The tool description adds no parameter-level detail, but with a single obvious parameter this is not a significant gap. The description neither enriches nor contradicts the schema.

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 ('Evaluate') and clearly identifies the resource: sensitivity of commercial conclusions, specifically channel rank order and iROAS, under alternative adstock and saturation priors. This distinguishes it from sibling tools like model fitting, prediction, or budget optimization even without naming them explicitly.

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 context of use is implied: this should be used when one needs to check whether prior choices materially affect commercial conclusions. However, it does not explicitly say when to use it versus alternatives like diagnose_mmm, compare_models, or cross_validate_mmm, nor does it provide exclusions or prerequisites.

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