compare_fit

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

With no annotations provided, the description carries the burden of disclosing behavior. It does disclose a meaningful statistical behavior: the optional chi-square difference test and its MLR scaling correction. However, it does not state that the tool is read-only, what happens on missing/invalid files, or any output/error behavior, leaving some behavioral ambiguity.

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?

The description is compact and front-loaded with the core action, then expands with relevant use cases and the chisq_diff behavior. It earns every sentence, though it could be slightly more structured by separating the parameter-specific behavior from the general purpose.

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 description is adequate for invoking the tool: it explains the core comparison task, the chisq_diff option, and MLR scaling. However, with no output schema, it does not describe the return format or what the side-by-side table looks like, and it does not mention the nested-models prerequisite for the chi-square difference test, which an agent would need for correct usage.

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 coverage is 100%, so the baseline is 3. The description adds value beyond the schema by explaining that chisq_diff runs a chi-square difference test between consecutive models and that MLR scaling is handled, which the schema's one-line description does not convey. It also confirms the side-by-side ordering implied by out_paths.

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 verb ('Put ... side by side') and resource ('fit statistics of several .out files'), making the tool's core function unmistakable. It also lists concrete use cases (class enumeration, measurement invariance, nested model comparisons) and thereby distinguishes itself from single-file siblings like output_summary or output_section.

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 clear context for when to use the tool: whenever multiple .out files need their fit statistics compared. It does not explicitly name alternatives or say 'use only for multiple files,' so it falls short of a full when/when-not statement, but the multi-file framing is clear enough.

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