model_predict

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

With no annotations, the description must carry the behavioral burden, and it does reveal key mechanics: for `at`, 'holding everything else at its average' and using original data when neither argument is passed. It stops short of describing the output format or how conf_level/type alter results, leaving some behavior implicit.

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 sentences with code-formatted arguments, front-loaded main purpose, and no filler. Each clause earns its place by explaining a distinct mode or example.

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?

The tool has six parameters, no output schema, and no annotations, so the description must cover a lot. It explains the central at/newdata distinction thoroughly, but it never states what the result looks like (e.g., a table with predictions and confidence intervals) or how type/conf_level affect the output. This leaves an agent guessing about return shape.

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 input schema already documents every parameter, so the baseline is 3. The description adds valuable meaning by explaining what `at` computes (estimated marginal means with other predictors at their average) and contrasting it with `newdata` and the default fitted-value behavior. This goes beyond the schema's terse field descriptions.

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 opens with 'Predictions from a fitted model', which clearly states the tool's verb and resource. It goes on to explain three distinct prediction modes (at, newdata, neither), making its scope evident. However, it never references sibling tools like model_diagnostics or model_compare, so it doesn't explicitly differentiate itself.

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 description gives explicit rules for choosing among the three modes: use `at` for marginal means, `newdata` for specific new cases, and neither for fitted values. It even flags `at` as 'the usual way to describe what a model implies.' However, it does not discuss when to prefer this tool over a sibling tool such as model_compare or regression.

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