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

Adds real context beyond the readOnlyHint/openWorldHint annotations: the message is not stored, the message type is derived from the namespace rather than a required argument, and the return payload is described in detail (valid flag plus every problem with line, element path, stable code, plain reason). It stops short of disclosing limits or edge behavior such as oversized input, and the 'same code as <URL>' line is a provenance claim rather than behavioral information.

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?

Dense and front-loaded: scope, then validation layers, then return shape, then side-effect guarantees. Minor waste in re-listing all eight message types already present in the enum, and the trailing URL reference earns little space for the agent.

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 no output schema, the description correctly carries the return-value burden by describing the valid flag and the structure of each reported problem. Side effects and type-inference are covered; what is missing is anything about input size limits or failure modes when the XML is unparseable.

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; the description adds meaning beyond it by clarifying that type selection defaults to the namespace (making 'message' a read-only override) and by spelling out which rule families 'schema_only' skips (check digits, totals, cross-element rules, market practice). It never names 'schema_only' directly, so the mapping must be inferred.

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 ('Check') and a specific resource (one ISO 20022 XML message), then enumerates the eight supported message types and the two validation layers (base schema, then business rules). This is clearly distinguishable from siblings like list_messages or the verify_* tools, which do not validate ISO 20022 XML.

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?

Usage is implied rather than stated: the tool validates a message you already have, and the 'XML' and 'message' params suggest pre-send checking. However, there is no explicit when-to-use vs. when-not, no mention of what to do with the resulting problems (e.g. route to explain_issue), and no guidance relative to siblings such as list_messages.

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