Meridian roi by channel

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorld, so the trailing 'Read-only' is pure repetition. The one piece of added context is the 'fitted MMM' precondition, which hints at a failure mode for unfitted models; nothing is said about row volume, pagination, or response shape.

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?

A single front-loaded sentence with the resource and scope stated first and zero filler. Every clause carries 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?

An output schema exists, so return values need not be explained, and the tool is a simple one-parameter read. Still missing is how an agent obtains a valid model_id and whether the call fails or returns empty for an unfitted model, which matters given the 'fitted' qualifier.

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?

Only one parameter and the schema gives it zero description coverage, so the description must carry the burden. '(by model_id)' does tie the parameter to a fitted model identifier, which is more than the schema says, but it gives no format, source (e.g., which sibling lists model_ids), or error behavior for an unknown id.

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 the specific resource returned (per-channel ROI / contribution rows) and the scope (a fitted MMM keyed by model_id). This distinguishes it from meridian.model.summary and meridian.fit by output content, though the verb is implicit ('rows for') rather than an explicit action.

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 on when to choose this over meridian.model.summary, meridian.budget.optimize, or meridian.fit, and no statement of prerequisites beyond the passing phrase 'fitted MMM'. The agent must infer that a model must already be fitted before calling.

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