mfc_ca_getTaxes

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states 'retrieves tax classifications,' which implies a read operation but discloses nothing about return format, whether active/inactive entries come back by default, or any side effects. For a retrieval tool with zero annotation coverage, an agent is left without confirmation of read-only behavior or what a successful response looks like.

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 a single short sentence with zero wasted words. However, it borders on under-specification — one Japanese sentence that essentially translates the tool name. It's concise to the point of being thin, so while nothing needs cutting, the brevity sacrifices substantive guidance that would earn a higher score.

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?

For a simple getter with 2 optional, well-documented parameters and no nested objects, the schema carries much of the load. The description states the tool's purpose but, with no output schema present, fails to describe the return value format — a notable gap for a retrieval tool where an agent would want to know what tax data comes back. The tool appears self-contained but leaves the agent guessing about response shape.

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% — both parameters are thoroughly documented in the schema itself. The 'available' parameter is well explained (true=active only, false=all including inactive, with an explicit caution that false is not 'only inactive'), and 'office_code' covers format (XXXX-XXXX) and auth requirements (required for API key auth, omittable with MF_OFFICE_CODE). Since the schema fully documents both parameters, the baseline of 3 applies; the description adds no parameter meaning beyond what the schema already provides.

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 '税区分を取得します' states a specific verb (取得/retrieve) and a distinct resource (税区分/tax classifications), which differentiates it from siblings like getAccounts, getDepartments, and getTradePartners by entity type. However, the description is essentially a Japanese restatement of the tool name itself — an agent gains little beyond a translation of 'getTaxes'. It's clear, but the value added over the name is minimal.

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 offers zero guidance on when to use this tool versus the many siblings. No when/when-not conditions, no alternative tool pointers, no context about typical usage (e.g., fetching tax categories before creating journals or transactions). The schema's parameter descriptions hint at authentication scenarios (office_code needed for API key auth), but the description itself provides no usage direction whatsoever.

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