Run Evidence Judge Pass

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

All annotations are false, so the description carries the full burden of behavioral disclosure. It discloses the token requirement, the judge peer's role, the 'cannot judge its own ask' constraint, the promotion rule (satisfied=true and confidence='verified'), that everything else stays open, that terminal statuses are untouched, and that shadow_mode is non-mutating. These details go well beyond a generic tool statement and make side effects predictable.

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 about four sentences and packs a lot of information without being overly verbose. The opening sentence establishes the purpose, and subsequent sentences detail behavior. There is minor redundancy (e.g., 'Operator-authorized' and 'Requires the dedicated operator capability token' could be merged), but overall it is efficiently structured and front-loads the core action.

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 tool with 9 parameters, no output schema, and zero param descriptions, the description covers the core process well (what items it operates on, promotion rules, exceptions) but omits parameter semantics for most fields and does not describe return structure. It gives enough for a basic invocation but not enough to use optional parameters like round, item_ids, review_focus, or response_format effectively. The complexity warrants more detail.

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 0%, so the description must compensate. It adds meaning only for 'draft' (the supplied text) and 'judge_peer' (the configured reader), with no explanation of the other 7 parameters (session_id, round, caller, item_ids, review_focus, response_format, shadow_mode). An agent would have to infer or guess the role of item_ids, review_focus, and response_format. This is a significant gap given the low schema coverage.

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 specific verb ('judge pass'), a specific resource ('Evidence Broker'), and what it does: runs an LLM satisfied-detection pass over open checklist items. It also names the sibling it is not (consensus pass) indirectly by calling itself a judge pass. The distinction from related tools is clear enough for an agent to route correctly.

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 provides clear context: it requires an operator token, operates on currently-open items, and promotes only satisfied+verified items. However, it does not explicitly state when to prefer this tool over the consensus pass or other sibling tools, nor does it mention exclusions beyond 'terminal operator statuses and already-addressed items.' No alternative is named, so guidance is implied rather than explicit.

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