jev_confidence_gate

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

With no annotations, the description carries the full burden, and it does disclose useful traits: local execution, determinism, no API call, and that provider is validated against a registry while the gate itself is provider-agnostic. It omits what happens on an unregistered provider (error vs fallback) and does not explain what the `below` value contributes to the output, leaving meaningful behavioral gaps.

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 rule is front-loaded in the first sentence and the supporting facts (local, no API call, provider-agnostic) follow compactly with no filler. The reStructuredText double-backtick markup is slightly noisy but does not obstruct reading.

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?

An output schema exists, so return values need not be described, and the core conditional logic is fully specified. However, for a 5-parameter tool with entirely undocumented schema fields, the description leaves `below` unexplained and says nothing about provider validation failure, so it is adequate but not 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 0%, so the description must compensate, and it does explain the core semantics: the comparison of confidence against threshold and the resulting choice/bypass branch. It also clarifies that provider only affects registry validation, not gate logic. The `below` parameter (default 'review') is left undefined, which keeps it short of a 5.

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 states a concrete conditional rule ('Return choice when confidence >= threshold, else below') and names the resource as a confidence gate, so the operation is unambiguous. It also signals this is local routing rather than an API call, which separates it from API-backed siblings like jev_ask, though no sibling is named explicitly.

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?

Usage is implied rather than stated: 'routing over a synthesized choice answer' tells the agent this consumes an already-produced answer, and 'no API call' implies it is the cheap deterministic path. There is no explicit when-to-use versus jev_tiered_gate or jev_evaluate, and no conditions that would make this the wrong choice.

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