beam

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

With no annotations, the description fully discloses behavior: parallel execution, scoring, best-effort budget cap, preservation of losers, evaluator cost exclusion, and return format. It covers edge cases like budget exhaustion and all-zero scores, and explains the search stamp recording.

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 a clear lead sentence, bullet points, and sections. It is thorough but not overly verbose; every sentence adds value. Minor conciseness could be improved by merging some explanations, but overall it is efficient.

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 ten parameters, no schema description coverage, and an output schema that exists, the description covers all aspects: input semantics, behavioral quirks, return schema, error handling, and anti-patterns. It leaves no obvious gaps for an agent to understand when and how to invoke the tool.

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 0%, so the description must compensate, and it does comprehensively. Every parameter is explained with context—e.g., evaluator must start with 'score:' or 'validate:', default values, and the effect of 'keep_losers' on preserving alternatives. This adds substantial meaning beyond the schema's basic type definitions.

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: 'Sample N candidates in parallel, score each, commit to the top-1.' It clearly distinguishes from sibling tools like 'par' and 'race' by explaining it's a search combinator with scoring, comparing to self-consistency/majority-vote.

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?

It provides explicit guidance on evaluator forms (score: vs validate:) and when to use each. It mentions an anti-pattern (expensive evaluator) and recommends using a governor instead. However, it does not explicitly contrast with all sibling tools like 'chain' or 'map', leaving some usage context implicit.

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