Meridian.Model.Summary

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

With no annotations provided, the description carries the full burden, and it does add two useful traits: 'Read-only' (safe, non-mutating) and 'cheap' (low cost/latency signal). It stops short of disclosing failure behavior for an unknown model_id or whether rows are paginated, which matters for a no-annotation tool.

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 short fragments, front-loaded with the resource and then the qualifier — nothing wasted. The word 'cheap' is informal and slightly vague, but it conveys a real selection signal for an agent choosing among meridian tools.

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 has only one parameter. What remains missing is the provenance of model_id and error/empty behavior — modest gaps, but meaningful for a tool with zero annotation and zero schema-text support.

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%, so the description must compensate for the single model_id parameter. '(by model_id)' does clarify that the parameter keys the lookup to a previously fitted model rather than a new one, but it never says where model_id comes from (presumably the response of meridian.fit) or its format.

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 names a specific resource — fit-summary rows — and scopes it to 'an already-fitted MMM (by model_id)', which tells an agent this is a retrieval of diagnostics, not a fitting operation. It is distinguishable from meridian.fit and meridian.roi.by_channel by resource, though it never names those siblings 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?

'for an already-fitted MMM' implies the prerequisite that a fit must exist first, and 'cheap' hints this is a low-cost call to prefer over re-fitting. However, there is no explicit statement of when to call this versus meridian.roi.by_channel or meridian.budget.optimize, and no guidance on what to do if no fit exists.

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