Convert MT202 to pacs.009 fields

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 discloses that the tool 'returns notes on anything not confidently mapped,' which is valuable transparency about output behavior. It clarifies the semantics of what MT202 maps (institution BICs only, no Dbtr/Cdtr) which helps the agent understand edge cases. It doesn't mention error behavior or input validation requirements, but the core mapping behavior and its limitations (unmappable fields) are disclosed.

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 two well-structured sentences that cover purpose, field mapping, the MT103 contrast, and the 'notes' return behavior. It's front-loaded with the primary action and resource. Slightly long but each component earns its place; no wasted words.

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?

With 1 param, 100% schema coverage, and no output schema, the description provides strong context: what it maps, which fields, how it differs from MT103, and what it returns with unmappable data. For a single-input, mapping-type tool, this is reasonably complete. It could mention the output format (JSON structure of returned notes) but the essential context is present.

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% (1 param fully described: 'The raw MT202 message body'), so the schema does the heavy lifting. The description's mention of 'Parses a SWIFT MT202' implies the input is a raw message body matching the schema's description. The description adds little beyond the schema for the single parameter, so 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 clearly states the verb ('parses', 'maps') and specific resources (MT202 message → pacs.009 fields), and explicitly lists the target fields (MsgId, EndToEndId, IntrBkSttlmDt, etc.). It also distinguishes itself from sibling tools by contrasting MT202 vs MT103 and noting the absence of customer-level Dbtr/Cdtr in MT202. This is a specific, well-differentiated purpose.

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 explains when this tool is appropriate (bank-to-bank transfers where only institution BICs exist) and explicitly contrasts with MT103, implying the alternative convert_mt103_to_pacs008 tool is for customer-level data. It doesn't formally state 'use X instead when Y', but the behavioral contrast between MT103 and MT202 gives clear context. A dedicated when-not-to-use statement would push to 5.

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