mc_synth

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

Annotations already declare readOnlyHint=true, and the description adds valuable behavioral context: assumptions (SUTVA, no anticipation), pre-conditions, failure modes, and typical minimum N. It does not contradict the annotations and adds transparency about convergence/tracking failures and placebo inference caveats.

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 long but well-structured with labeled sections (Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N). Each section earns its place by informing tool selection and invocation, though the opening is a noun phrase rather than a concise actionable statement.

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 an output schema exists and schema coverage is 100%, the description does not need to explain return values or every parameter. It covers assumptions, preconditions, failure modes, and alternatives, which is strong contextual support for an agent deciding whether and how to invoke this 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 coverage is 100%, so the schema carries the parameter documentation burden. The description adds conceptual context (donor units, pre-treatment window, RMSPE) but does not describe specific parameter syntax, defaults, or how parameters map to the method's inputs. This is acceptable given full schema coverage but adds limited parameter-level value.

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 identifies the method as 'Matrix Completion Synthetic Control Method' and provides assumptions that imply it estimates treatment effects using donor units to construct a counterfactual. However, it lacks an explicit verb phrase such as 'estimates the causal effect of a treatment on a treated unit', and it does not clearly differentiate itself from siblings beyond listing alternative names.

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 provides explicit pre-conditions (panel structure, pre-treatment window, complete outcome data) and lists alternatives. It also gives conditional guidance in failure modes, e.g., when pre-treatment RMSPE is large it suggests sdid/augsynth. It stops short of explicitly saying 'use this tool when X and not when Y', but the context is largely inferable.

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