meridian.fitFits a Bayesian marketing mix model to a referenced dataset using a supplied configuration and returns a model or job handle for tracking compute-heavy MCMC sampling.
Fit a Bayesian MMM on dataset_ref with config; returns a model/job handle. Read-only (no account mutation) but COMPUTE-HEAVY: MCMC sampling, minutes-to-hours.
| Name | Required | Description | Default |
|---|---|---|---|
| config | Yes | ||
| dataset_ref | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.5.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses the read-only/no-mutation safety profile, the MCMC sampling workload, and the multi-minute to multi-hour latency. It leaves open whether the call blocks or returns immediately, though 'job handle' hints at asynchronous behavior.
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?
Two tight sentences with the operation stated first and the cost/safety caveat second. No filler; every clause carries information an agent would act on.
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 spelled out, and the safety/compute profile is covered. But for a tool whose only configuration path is an undocumented free-form nested object, the description is too thin to let an agent construct a valid `config`.
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%, and the free-form nested `config` object is completely opaque. The description names both parameters but explains neither what `dataset_ref` points to nor what keys `config` accepts, so it adds almost no meaning beyond 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?
States a specific verb and resource ('Fit a Bayesian MMM on dataset_ref with config') plus the return artifact ('model/job handle'). The resource is clearly distinct from siblings like meridian.model.summary and meridian.budget.optimize, but the description never explicitly contrasts them.
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 compute-heavy warning ('minutes-to-hours') is a real invocation consideration, implicitly telling the agent to use this deliberately rather than casually. However, there is no explicit guidance on prerequisites, what to do with the returned handle, or when to call meridian.model.summary instead.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.