correct_classification

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

With no annotations, the description carries full burden. It discloses that the tool uses '永続記憶' (persistent memory) and will '自動適用' (automatically apply) corrected categories to future similar transactions. It also explains scope options (company-wide or specific company). While it doesn't cover all behavioral details (e.g., idempotency, error handling), it provides key behavioral context beyond the schema.

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 three sentences long with no filler. It front-loads the core purpose ('税理士修正フィードバック'), explains the mechanism, and notes scope. Every sentence earns its place, making it highly concise and well-structured.

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 tool's complexity (8 parameters, persistence, auto-application), the description covers the main purpose, behavior, and scope. It lacks details about return values (no output schema) and error handling, but these are not critical for understanding the tool's function. Overall, it is reasonably complete for a correction feedback tool.

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%, meaning each parameter already has a description in the input schema. The tool description adds conversational context but does not provide additional parameter-level meaning beyond what the schema already conveys. Per guidelines, baseline is 3 when coverage is high.

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 explicitly states '税理士修正フィードバック' (tax accountant correction feedback) and explains the tool records misclassifications and auto-applies corrected categories to future matching transactions, with a note about persistent memory. This clearly distinguishes it from siblings like 'classify_transaction' (classification) and 'recall_memory' (memory retrieval), providing a specific verb-resource pair.

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 clearly indicates the tool is for correction feedback and mentions scope (company-wide or per-company). It implicitly distinguishes from siblings by focusing on recording corrections rather than classifying or recalling, but does not explicitly state when NOT to use it or name alternatives. This is slightly below a 5 due to lack of explicit exclusion guidance.

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