Validate SWIFT MT message

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

No annotations are provided, so the description carries the burden of disclosure. The description enumerates rule categories (mandatory fields, format rules, IBAN checksums) which surfaces behavioral scope. However, it does not disclose what happens on validation failure (return format, error granularity), whether it only checks or also modifies anything, or whether there are rate/input-size limits. Given zero annotations, this leaves notable gaps but the rule catalog is genuinely useful.

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?

Two sentences, zero wasted words. Front-loads the purpose and scope immediately, then gives concrete usage context. The sentence about rules is dense but every clause contributes information. No redundancy with larger framing.

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?

The tool has moderate complexity (two message types, multiple validation rule categories, 2 simple parameters, no output schema). The description covers purpose, scope, what's validated, and when to use it. It doesn't describe the return/result format, but without an output schema the agent may need to know what 'validated' returns. Still, given the 2-param surface and clear rule enumeration, it's adequately complete for selection purposes.

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 helpful descriptions for both parameters (message_type with enum, raw_message with example format ':20:REF123\n:23B:CRED\n:32A:...'). The description adds that message_type supports only MT103/MT202 (consistent with schema enum) and clarifies raw_message is a 'body' with field tags, reinforcing the schema. With full schema coverage, this is solid; the description complements rather than repeats.

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 specific verbs ('Validates') and resources (SWIFT MT103/MT202 message bodies), enumerating exactly what is validated: mandatory-field rules, field-format rules for dates/currency/BIC/charges code, and IBAN checksums. It distinguishes from sibling validation tool 'validate_iban' by being the message-level validator rather than the single-IBAN validator.

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?

Provides explicit usage guidance: 'Use this before submitting or forwarding an MT message, or when an agent needs to check a message it generated or received is well-formed.' This clearly establishes when to invoke the tool. While it doesn't name an explicit alternative for when NOT to use it, the sibling list and the specific scope (MT103/MT202 only) implicitly communicate boundaries, and the example check scenario is concrete and actionable.

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