Evaluate Continuation Nudge

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

Annotations already cover safety (readOnly, idempotent, non-destructive), yet the description still adds real behavioral context: the veto conditions on user input and on repeated no-progress nudges, and the exact shape of the returned decision fields. Disclosing that veto behavior is exactly the kind of trait structured fields cannot convey.

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?

Front-loaded with the core decision, then structured into use/do-not-use/returns blocks that are quick to scan. The only waste is enumerating the six workflow phases twice, once in the opening sentence and again in the Returns line.

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 three-parameter decision tool with no output schema, the description supplies the trigger condition, the exclusions, the veto logic, and the full return contract including the action enum and confidence range. An agent has everything needed to decide whether to call it and how to read the result.

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 baseline is 3. The description hints at the role of progress history ('repeated nudges make no progress'), which loosely motivates previous_nudge_summary, but it says nothing about how threshold interacts with the decision or what the returned confidence value means relative to it.

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 decision object: it evaluates whether an agent paused prematurely, enumerates the workflow phases covered, and states it can veto nudges. That is far more than a restatement of the name. It does not, however, differentiate itself from the near-synonymous sibling jev_verify_completion, leaving an agent to guess which to call.

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 explicit 'Use when' / 'Do NOT use when' pair gives a clear triggering condition (a background worker or loop stops) and a clear exclusion (explicit request for confirmation or credentials). What is missing is the alternatives axis: it never says which sibling to call instead when the agent stopped for legitimate user input.

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