mf_expense_upload_receipt

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

With no annotations, the description carries the full burden and does so unusually well: it discloses the non-obvious side effect that an upload may auto-create an expense entry via OCR, warns about double-counting, and states that credentials-directory files are rejected. It does not mention authentication requirements or file size limits, leaving a gap for a mutation tool.

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 action is front-loaded, followed immediately by the highest-risk warning in bold. Every sentence adds a distinct piece of information (side effect, sibling interaction, extensions, credential-dir rejection) with no filler.

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 two-parameter tool with no output schema and a surprising mutation side effect, the description covers the critical behaviours (auto-creation, double-count risk, file constraints) well. Authentication prerequisites and any return-format detail are the only meaningful omissions.

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 100%, so the baseline is 3, but the description adds meaning on top of the schema by enumerating the exact allowed extensions (jpg/jpeg/png/gif/heic/heif/pdf) that constrain the file_path parameter. office_id remains undocumented beyond the schema.

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?

States a specific verb and resource ('レシート画像・PDF をアップロードします') and immediately distinguishes itself from the sibling mf_expense_create_transaction by explaining the OCR auto-drafting behavior. An agent can identify the tool's role without opening the schema.

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 names the condition and the alternative: if you intend attachment-only but also call mf_expense_create_transaction, you risk double-counting, so verify the resulting '作成された明細数'. This is a concrete when/when-not routing instruction, not an implied one.

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