bridge

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

Goes well beyond the readOnlyHint annotation by disclosing assumptions (e.g., target estimand must match), pre-conditions (data shape, kwargs), and failure modes (agreement test rejection implies assumption violation). It also mentions the doubly-robust property of the combined estimate. This is rich behavioral disclosure that helps an agent anticipate outcomes.

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 longer than the minimal ideal but each section (purpose, assumptions, pre-conditions, failure modes) earns its place for a complex dispatcher. It is front-loaded with the core purpose and then abuts relevant usage constraints. Slightly verbose but not redundant.

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 tool's complexity and the presence of an output schema, the description is comprehensive: it lists all six bridge types, specifies assumptions and pre-conditions, and mentions failure modes. It does not need to explain return values because the output schema exists. It equips an agent with enough to invoke 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?

Schema coverage is 100%, so the baseline is 3. The description adds valuable parameter-related context, such as the meaning of the 'kind' values (mapping theorem pairs) and giving an example of required columns for 'did_sc'. This goes beyond the schema's 'Which bridge to invoke' and helps agents map inputs to the correct bridge.

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?

Clearly states it is a 'unified dispatcher' for six specific causal-inference bridging theorems, naming each pairing (e.g., 'DiD==SC', 'IPW==DR==CB'). The verb 'bridge' and resource are specific, and the description distinguishes it from single-estimator siblings by focusing on path estimates plus a doubly-robust recommendation.

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?

Provides clear context on when it applies: it enumerates the six bridge types, states pre-conditions (per-bridge kwargs, panel shape) and references failure modes. It does not explicitly name alternative tools to use instead when one only needs a single estimator, but the specification of bridging targets implicitly guides selection.

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