trimming

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

Annotations already establish readOnlyHint=true, so the description does not need to restate safety. It adds valuable context by disclosing statistical assumptions, preconditions, failure modes, and a typical minimum N. It does not describe return payloads, but the output schema exists and the schema documents as_handle caching, so this is not a major gap.

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 front-loaded with the purpose and then organized into labeled sections for assumptions, pre-conditions, failure modes, alternatives, and typical sample size. Each section earns its place, and the formatting makes it easy for an LLM to scan.

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 an 11-parameter causal-inference tool, the description covers when to use it, required data conditions, what can go wrong, what to do about it, and alternatives. With a 100%-covered schema and an output schema present, nothing essential is missing for selecting and invoking the tool.

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 baseline is 3 even without parameter details in the description. The description adds conceptual context for covariates, treatment, and overlap, but it does not explain parameter-specific choices such as crump vs sturmer beyond what the schema already provides.

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 first sentence, 'Trim sample to optimal overlap region,' uses a specific verb and resource and clearly distinguishes this from sibling tools like overlap_plot or overlap_weights. It also names alternatives, making its role in the causal-inference pipeline unmistakable.

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 data pre-conditions and a decision rule under failure modes: trim when overlap is poor, and re-specify the balancing model when imbalance remains. This tells an agent when to use this tool and when to turn to alternatives.

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