xtnbreg

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

Annotations already declare readOnlyHint=true, so the agent knows this is a read-only operation. The description adds behavioral detail by explaining that model='fe' uses nbreg and model='re' uses menbreg, which hints at implementation behavior. It does not describe output structure, but an output schema exists, reducing the need. No contradictions with 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?

Two concise sentences with no filler. The purpose is stated first, followed by the key model-choice guidance and a critical warning. Every sentence earns its place, and the structure front-loads the most important information for an agent.

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 15 parameters and an output schema, the description covers the core decision (model selection) and a common pitfall (feols). It does not explain optional parameters like offset, exposure, or clustering, but those are well-documented in the schema. Given the rich schema and output schema, the description is sufficiently complete for an agent to call the tool correctly.

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 schema already documents 73% of parameters, including descriptions for model, detail, data_path, etc. The description adds meaningful semantics for the 'model' parameter by mapping 'fe' to nbreg and 're' to menbreg, which is not in the schema. It also reinforces that the outcome must be negative-binomial, helping agents avoid misusing parameters. This goes beyond the schema's baseline.

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+resource: 'Fit panel negative-binomial regression.' It clearly distinguishes the tool's domain (panel negative-binomial) and explicitly warns against using feols for such outcomes, which sets it apart from sibling tools like fepois or ppmlhdfe. The mention of model='fe' vs 're' further clarifies the two main modeling approaches.

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 guidance on when to use this tool: for panel negative-binomial outcomes, and explicitly advises against using feols. It also instructs how to choose between fixed and random effects via the 'model' parameter. However, it does not directly compare with other panel count tools (e.g., fepois for Poisson) or with nbreg/menbreg outside the panel context, leaving some room for inference.

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