Run Evidence Judge Pass

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

With no readOnlyHint (annotations all false), the description carries full burden. It discloses mutation of checklist state (promotes satisfied/verified items), notes items that are never touched, mentions the cap of 8 items, and explains that shadow_mode provides a non-mutating alternative. This is thorough, though idempotency and error behavior could be clearer.

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 verbose (over 150 words) and includes version numbers (v2.9.0, v2.10.0) that may not be useful for an agent. It is front-loaded with core purpose and structured logically, but could be more concise without losing essential details.

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 complexity (9 params, no output schema), the description partially covers the return format (structured judgment) and process. However, it omits parameter details for several fields, does not fully specify output in normal vs shadow mode, and lacks error or rate limit information. 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 description must document parameters. It explains draft, judge_peer, item_ids, and shadow_mode. However, it leaves session_id, round, caller, review_focus, and response_format undocumented. With 9 parameters and no schema descriptions, this is a significant gap.

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's purpose as an 'LLM-based satisfied detection for the Evidence Broker' that runs a judge pass. It specifies the action (run pass), the resource (open checklist items against a draft), and distinguishes from the sibling 'session_evidence_judge_consensus_pass' by implying single-peer judgment, but does not explicitly differentiate.

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 when to use the tool (for satisfied detection), identifies eligible items (open, not terminal, not addressed by resurfacing-inference), and mentions optional filters. However, it lacks explicit guidance on when not to use it or when to prefer siblings like 'session_evidence_judge_consensus_pass'.

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