model_compare

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

No annotations are present, so the description is the sole source of behavioral disclosure. It reveals that the likelihood-ratio or F test is only applied when models are nested, a conditional behavior, and implicitly indicates a read-only comparison rather than model modification. It does not describe output format or edge cases, but covers the key behavioral caveat.

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, each earning its place: the first states the core functionality and the second states the prerequisite. Purpose is front-loaded with no filler or schema-repetition.

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 tool with no output schema and no annotations, the description covers the core action, the metrics, the nested-model condition, and how to prepare inputs. It does not spell out the return value, but the purpose sentence implies the output, and the schema covers parameter details. This is complete enough for correct invocation.

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 all three parameters at 100% coverage, setting a baseline of 3. The description adds meaningful context by explaining that the models parameter refers to save_as names from prior regression/test_anova calls, which clarifies what value should be supplied beyond the schema's 'Names of fitted models in the session'.

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 a specific verb 'Compare' and a precise resource 'two or more fitted models', enumerating the metrics (AIC, BIC, log-likelihood, delta AIC) and the conditional test. This distinguishes it clearly from sibling model_diagnostics, which is for single-model inspection, and from regression/test_anova which fit models.

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?

It provides an explicit prerequisite: fit models first with regression or test_anova and assign save_as names. This tells an agent when it is ready to call the tool. It does not name alternatives or when-not-to-use cases, so it falls short of a full 5.

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