verify_claims

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

Annotations declare readOnlyHint, idempotentHint, and destructiveHint, but the description adds substantial behavioral context beyond that: L2 checks task codes, suppression rules prevent duplicate findings, derived values are skipped when their source is already flagged, and rounding tolerance maps to warning rather than error. No contradiction with annotations.

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 detailed but every section earns its place: purpose, L1-vs-L2 rationale, suppression rules, rounding policy, return shape, and usage examples. The key purpose is front-loaded and the examples are compact and useful. Length is justified by the tool's non-obvious verification logic.

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?

The description explains the tool's core evaluation logic, edge cases, suppression behavior, rounding tolerance, and return shape. With an output schema present and full schema coverage, nothing an agent needs to invoke this tool correctly is missing. It handles a moderately complex verification task comprehensively.

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 schema already documents all four parameters with names, defaults, and descriptions. The description adds general context about what 'verification' means and how findings are produced, but it does not add per-parameter meaning beyond the schema. Baseline 3 is appropriate.

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 resource: '보고서의 값을 원본과 대조합니다' (compares report values against the original), then defines the two finding levels L1 and L2. It distinguishes itself from siblings by explicitly naming check_completeness as the tool for missing items, so an agent can select 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 gives an explicit positive use case ('보고서 숫자가 원본과 맞나요?') and a negative case (missing items → check_completeness). It also documents important behavioral conditions such as suppression rules and when rounding differences become warnings, which helps the agent decide when and how to invoke the tool.

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