Convert MT103 to pacs.008 fields

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

With no annotations provided, the description carries the full transparency burden. It discloses that the output is a 'simplified field map plus notes on anything that couldn't be confidently mapped', setting honest expectations about output fidelity and partial mapping. It also discloses the scope limitation (not a full XML generator). This is solid behavioral disclosure, though it doesn't cover edge cases like malformed input handling or base64 requirements.

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 well-constructed sentence that front-loads the core action, enumerates mapped fields, discloses limitations, and notes intended use—all without redundancy. Slightly dense but efficient; no wasted words. Could arguably be split for readability, but it earns a 4 for packing value without bloat.

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 it has only 1 parameter with 100% schema coverage, no output schema, and no annotations, the description provides a good overview: input type, mapped fields, output shape ('simplified field map plus notes'), and scope boundaries. It's reasonably complete for a low-complexity tool. Minor gaps include no mention of error behavior on malformed input or character encoding considerations, but overall adequate.

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% with only one 'raw_message' parameter described well ('The raw MT103 message body'). Although the description repeats that it parses an MT103, it adds context by implicitly framing the parameter as the raw message needing parsing. With a single self-explanatory parameter at full coverage, there's little additional semantic burden on the description to carry. A 4 is appropriate since the description contextually supports what the parameter represents.

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'), resource ('SWIFT MT103 message'), and result ('maps its fields to the equivalent ISO 20022 pacs.008 fields'). It enumerates the specific fields mapped (MsgId, IntrBkSttlmDt, IntrBkSttlmAmt, Ccy, ChrgBr, Dbtr/Cdtr name and account), distinguishing it from sibling tools like convert_mt202_to_pacs009 and convert_pacs008_to_mt103 (reverse direction).

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 explicitly states what the tool does NOT do ('not a full XML generator') and its intended use case ('intended for agents that need a quick MT-to-MX field bridge'), which helps an agent decide when this is appropriate vs alternatives. However, it doesn't explicitly name sibling alternatives or state when-not-to-use conditions (e.g., when full XML output is needed).

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