policy_value

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the description is not required to repeat safety. It adds rich behavioral context: assumptions (causal_impact, matrix-completion, no concurrent intervention), pre-conditions, failure modes, and a typical minimum N. This goes beyond the annotations and gives the agent a realistic sense of when results are trustworthy.

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 well-structured with clear sections (Validation, Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N) and front-loads the core purpose. It is a bit lengthy but every sentence earns its place by adding decision-relevant context. The structure aids scanning, which is good 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?

The tool is complex (8 params, output schema present) and the description covers assumptions, pre-conditions, failure modes, alternatives, and a typical sample size. Given that an output schema exists, the description does not need to explain return values. It is complete for an agent to decide when to call it and how to interpret the result.

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 all 8 parameters are already documented in the input schema. The description does not add parameter-level detail beyond what the schema provides; it mentions 'binary policy recommendations' and 'doubly robust scores' but these are also in the schema. Baseline 3 is appropriate given high schema coverage.

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 and resource: 'Evaluate the expected value of a treatment policy.' It clearly distinguishes this tool from siblings by naming explicit alternatives (sp.synth, sp.sdid, sp.gsynth) and providing pre-conditions and failure modes that define its scope. This is a strong, differentiating purpose statement.

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 names three alternatives and provides pre-conditions (e.g., treated unit with pre-period and control series, or low-rank panel) and failure modes (poor pre-period fit, controls affected) that imply when to use this tool. However, it does not explicitly state 'use this when X, use synth when Y' with conditions tied to each alternative, so it stops short of full exclusion guidance.

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