Audit Estimate Against Fair Price

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

Annotations declare readOnlyHint=true and destructiveHint is false, confirming a non-mutating audit operation. But the description goes much further: it discloses the verdict values, the did_you_mean fallback for unmatched work names, and the unit_mismatch fallback for per-unit vs. total price confusion. These behavioral details are extremely valuable for an agent to set user expectations and handle edge cases.

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 dense but front-loaded: it starts with the core audit function徒, then the key usage signal ('when you have a specific quote'), then output format. The Japanese and English versions repeat each other, which adds length but serves the bilingual audience. It covers a lot in a compact form; only minor redundancy in the output field list between both languages keeps it from a 5.

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?

Despite having both input and output schemas with high coverage, the description adds essential usage context (when to use vs. the get_price_range and verify_fair_price alternatives), explains edge cases (did_you_mean, unit_mismatch), and clarifies the output shape. For a read-only audit tool with 2 parametersicc and strong annotations, this is 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 essentially 100%, so the baseline is 3acheter. However, the description adds critical context beyond the schema: it specifies that quoted_price should be the total for an itemized quote, that the value is passed as-is without tax normalization, and that the work name should include material and grade for better matching. It also explains the partial-match behavior and did_you_mean fallback. The schema already describes the parameters well, so the description's job is to add usage nuance — which it does thoroughly.

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 audits a quoted estimate against HORIZON SHIELD fair-price ranges for Japanese construction/renovation jobs, using a specific verb-resource pair ('audits', 'contractor quoted price'). It differentiates from siblings by naming alternatives (get_price_range, verify_fair_price) and mentions the return JSON structure including verdict, level, fair_range, and other fields.

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?

Explicitly states when to use: '手元に具体的な見積額がある時' (when you have a specific quote). It also gives clear exclusions and alternatives: '見積額が無く相場だけ知りたい時は get_price_range' (use get_price_range for typical ranges) and '署名付きの検証可能な証明が要る時は verify_fair_price' (use verify_fair_price for signed verifiable proofs). Also notes Japan-only and JPY.

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