aetre_sequential_stopping_rule

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

With no annotations provided, the description carries the full disclosure burden, yet it discloses little beyond the action itself. It does not state the return format (what the boundaries look like), error or edge-case behavior (e.g., empty reviews array), or any numerical caveats. The read-only nature is only implied by the non-mutating verb 'Calculates', which is the sole behavioral signal.

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?

A single sentence of roughly twenty words with zero redundancy. The primary action is front-loaded ('Calculates optimal dynamic Bayesian stopping boundaries'), followed by the decision outcomes and the driving mechanism. Nothing in the description is wasted, packing the core semantics into minimal length.

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 fairly complex statistical tool with 8 parameters, no output schema, and no annotations, the description is thin. It omits the return structure of the boundaries, usage context, and the relationship between the optional cost/confidence/noise parameters and the stopping decision. The schema covers parameter meanings, but the operational context an agent needs to call this correctly is under-specified.

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 the schema already documents all 8 parameters (prior_mean, prior_variance, threshold, reviews, next_review_cost, confidence_threshold, next_review_noise_sd) with examples. The description adds only the conceptual tie-in of 'posterior decision confidence and boundary VOI' as the basis, which lightly frames confidence_threshold but does not materially extend the schema. The coverage-based baseline of 3 holds.

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 uses a specific verb ('Calculates') with a specific resource ('optimal dynamic Bayesian stopping boundaries for sequential reviews'), enumerates the three decision outcomes (Accept, Reject, Solicit More Reviews), and names the mechanism (posterior confidence and boundary VOI). It is topic-distinct from the VOI siblings (aetre_calculate_voi, aetre_heavy_tailed_voi), so an agent can broadly tell it apart, though no sibling is explicitly named.

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?

No guidance is given on when to use this tool versus the many related VOI or posterior-tool siblings (e.g., aetre_calculate_voi, aetre_heavy_tailed_voi, aetre_triage_proposal). There are no conditions stated for when its stopping-boundary logic is appropriate, nor any exclusions or alternative routing. Usage must be inferred from the purpose phrasing alone.

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