Run Evidence Judge Pass

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

Goes well beyond annotations by disclosing the promotion rule (satisfied=true AND confidence='verified'), that non-qualifying items stay open, that terminal and already-addressed items are never touched, that shadow_mode is non-mutating, and that a verified capability token is required because the pass spends the petitioner's paid-provider budget. These are the exact side effects an agent needs before invoking a mutating, open-world tool.

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 purpose, then layered with behavioral rules in a logical order; every sentence carries information about gating, scope, or cost. It is dense and slightly long, but no sentence is filler, so it stays efficient for the complexity of the tool.

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 complex 9-parameter mutation tool with no output schema, the description covers most of what an agent needs: judge semantics, promotion criteria, preservation guarantees, and the auth/budget requirement. It stops short of describing the returned judgment shape and omits meaning for several parameters, which keeps it from being fully 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 only partially: it clarifies draft, judge_peer ('configured judge peer'), shadow_mode, and the caller requirement (petitioner capability token). It leaves round, item_ids, review_focus, and response_format entirely unexplained, so several parameters remain opaque from both schema and description.

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?

States a specific function ('LLM satisfied-detection for the Evidence Broker') and the concrete mechanism: the judge peer reads each open checklist item against the draft and returns a judgment. An agent can tell this is the single-peer judge pass, but the description never explicitly names or contrasts the obvious sibling session_evidence_judge_consensus_pass, so differentiation is inferred rather than stated.

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 through behavior (judge reads open items, promotes satisfied ones), and one hard constraint is given ('a peer can never judge its own evidence ask'). However, there is no explicit statement of when to choose this pass versus session_evidence_judge_consensus_pass or any alternative, nor of prerequisites such as the session needing to be in a specific state.

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