Recommend efficiency thresholds

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

Annotations indicate readOnlyHint=true and openWorldHint=false. The description adds transparency by listing which thresholds are adapted, the fallback behavior with derived_from_corpus bool, and the fact that four thresholds stay at hardcoded defaults. No contradiction with 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, front-loading the core purpose, then detailing thresholds, filtering, fallback, and return fields. Every sentence provides necessary information without redundancy.

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 existence of an output schema, the description covers the essential aspects: what it does, how to filter, fallback, and return structure. It could clarify the meaning of 'adapted' vs non-adapted thresholds, but is generally complete.

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 low (20%), but the description compensates by explaining the purpose of days, backend, metric, and k for filtering corpus history. It does not detail default values or allowed ranges, leaving some ambiguity.

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 clearly states the tool computes corpus-percentile thresholds from efficiency observations history. It names specific thresholds and distinguishes itself from other recommend_* tools by focussing on efficiency thresholds adaptation.

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 explains how to filter by days, backend, metric, and k, with concrete examples like 'what's normal for HNSW+cosine+k=10'. It also describes fallback behavior when corpus is small. However, it does not explicitly state when not to use this tool or mention alternatives.

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