melogit

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

The description discloses assumptions, pre-conditions, and failure modes, which is valuable context beyond the readOnlyHint annotation. It tells the agent what could go wrong and what remedial steps to take, and it does not contradict the annotations.

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 organized into labeled sections and packs substantial information into a compact form. The phrase 'Validation: certified parity evidence' is cryptic and somewhat unexplained, but the rest of the content is purposeful and front-loaded.

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?

Given the model complexity, 12 parameters, and an output schema, the description covers assumptions, pre-conditions, failure modes, and alternatives. It could be slightly more complete by explicitly connecting failure-mode advice (e.g., increasing quadrature points) to the nAGQ parameter, but overall it gives enough context 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?

Schema description coverage is 100%, so the schema already documents all parameters. The description reinforces that the outcome must be binary and that a grouping variable is required, but it does not add meaning for specific parameters like nAGQ, x_random, or detail beyond what the schema already says.

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 clearly identifies the tool as random-effects logistic regression and gives Stata's melogit as an anchor, so an agent can recognize the model family. It does not explicitly distinguish it from sibling mixed-model tools like meglm or meologit, and the named alternatives (sp.mixed, sp.regress) are not in the provided sibling list, which slightly weakens differentiation.

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 pre-conditions (binary outcome, grouping variable), failure modes (non-convergence, near-zero variance, perfect separation), and a typical minimum N give concrete context for when to call this tool. It does not explicitly say when to prefer meglm/meologit/logit over this tool, though the failure-mode advice to fall back to ordinary logit is useful.

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