snips

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

Beyond the readOnlyHint annotation, the description discloses the statistical tradeoff ('trades a small bias for large variance reduction'), the identification assumptions, the failure mode when 'effective sample size is tiny', and a remedial strategy. This gives the agent a truthful model of the estimator's behavior and limitations.

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 dense but every clause earns its place: method, tradeoff, assumptions, preconditions, failure mode, alternatives, and sample size guidance. It is front-loaded with the essential identity of the tool and uses compact labelled sections rather than rambling prose.

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 a 13-parameter estimator with an output schema, the description provides the statistical context an agent needs: identification conditions, required inputs, failure modes, alternatives, and sample-size guidance. Return-value details are covered by the output schema, so nothing critical is missing.

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, but the description adds semantic roles beyond the schema: X is 'context', A is 'logged action', R is 'reward', and it mentions 'logging propensities' as a precondition. This clarifies what the opaque parameter names mean, though many params (clip, alpha, detail) are not discussed in the description.

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 tool as a specific estimator ('Self-normalised IPS') and explains its purpose: 'bias-reduction for large IS weights'. It distinguishes itself from related methods by naming alternatives (sp.ips, sp.doubly_robust, sp.direct_method) and by stating the bias-variance tradeoff, so an agent can tell it apart from sibling tools.

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 explicitly says when the method is appropriate ('under heavy importance weights'), states assumptions, pre-conditions, and failure modes, and names concrete alternatives including when to switch ('switch to the doubly-robust estimator'). It also gives a practical 'Typical minimum N: 500' guardrail, which is actionable selection guidance.

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