breakdown_frontier

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

Beyond the readOnlyHint annotation, the description discloses key behavioral traits: the result is an interval, not a point; assumptions are weak; failure modes are described (bounds too wide); and typical minimum N is noted. This gives the agent a clear picture of what the tool returns and when it may be uninformative, without contradicting the 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?

The description is well-structured with labeled sections (Validation, Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N) and front-loads the core purpose. Each section provides useful information, but the text is somewhat dense; a few details (e.g., validation tiers) could be trimmed without loss of essential guidance.

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?

With an output schema present and high schema coverage, the description provides sufficient context: purpose, assumptions, pre-conditions, failure modes, alternatives, and minimum sample size. It covers the domain-specific knowledge an agent needs to call the tool correctly, though it does not go into error-handling or output interpretation (covered by schema).

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 input schema has 100% description coverage, so the baseline is 3. The description does not directly map parameters (e.g., assumption, n_grid, detail) to the full schema, but it does provide conceptual context around the identifying assumption and pre-conditions. It adds some semantic value but does not compensate beyond the schema's thorough documentation.

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 names a specific method (Masten-Poirier breakdown frontier) and its purpose (qualitative conclusions), and explicitly lists sibling alternatives (sp.oster_delta, sp.lee_bounds, sp.manski_bounds), making it distinguishable. It does not include an explicit verb like 'computes' or 'calculates', but the tool name and context clearly imply the action.

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 clear context by detailing assumptions (weak set-identifying, interval result, Lee/Oster additions), pre-conditions (data for point-identifying analysis, binary selection for Lee bounds), and failure modes (bounds too wide -> add auxiliary restriction). It names alternatives and their distinguishing properties, but does not explicitly state 'use this when X' or 'use alternative Y instead when Z', leaving some inference to the agent.

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