Judgment Precision Report

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

Annotations already indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds valuable behavioral context: it walks shadow_decision events, correlates with subsequent checklist resurfacing, and explains the 'no ground truth' exclusion rule. No contradictions.

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 front-loaded with purpose and metric, then explains the algorithm and use case. It is detailed but efficient given the complexity, though slightly verbose for a report 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?

Given no output schema, the description explains the return values (TP/FP/TN/FN, precision/recall/F1) and the exclusion logic. It covers the use case and filtering options. Could be slightly more explicit about output structure, but overall complete for the complexity.

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 mentions filtering by session_id, peer, and since timestamp, covering three of four parameters. However, the 'response_format' parameter (default json) is not described. The description provides some context but not full detail for all parameters.

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 computes precision/recall/F1 and TP/FP/TN/FN counts for shadow judge decisions against empirical ground truth. It distinguishes from sibling tools like session_peer_reliability_report by specifying the exact metric and use case (deciding whether to flip a peer to active mode).

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?

It explains that the tool can operate on all sessions or a single session (via session_id), and can be filtered by peer or since timestamp. It also mentions an exclusion rule for decisions without ground truth. However, it does not explicitly state when not to use this tool or compare it to alternatives like session_peer_reliability_report.

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