scl_validate

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

With no annotations provided, the description carries the burden of behavioral disclosure. It does explain that default is referential integrity and that schema validation is syntax-only, which is genuinely useful behavioral context. However, it doesn't disclose what the output/return format looks like, whether it modifies anything (it doesn't say it's a read-only operation), or error-handling behavior. The behavioral traits described are meaningful but incomplete.

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 well-structured and front-loaded: the first sentence gives the core purpose, then it enumerates what the default check catches (useful detail), then handles the optional parameter. Every sentence earns its place. It's slightly longer than strictly necessary but the enumeration of referential issues provides real value for understanding scope. A minor deduction for the length of the issue list.

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 an output schema that presumably describes the validation results, so return format is handled there. The description covers the key decision point (xsd_path optional), clearly distinguishes referential vs schema validation, and its sibling differentiation is strong. It's reasonably complete for a validation tool with an output schema, though it could briefly note expected file format or that it takes an SCD/SCL file on disk.

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 description coverage is 0%, so the description must compensate. It does add substantial meaning for 'xsd_path' (that it's optional, must be user-supplied, what it's used for). However, the single required parameter 'path' gets no semantic explanation — the agent must infer it's the SCL file path. Given 0% coverage, the baseline would be low, but the description's handling of xsd_path partially compensates while the primary 'path' param remains under-explained.

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 tool 'validates an SCL file's internal consistency, and optionally against an XSD schema.' It goes further to specify the exact scope ('referential integrity') and enumerates what that check catches: control blocks pointing at missing datasets, duplicate IPs, empty datasets, etc. This is a specific verb+resource with detail that distills the purpose from siblings like scl_check_goose_bindings.

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 explains that xsd_path is optional and provides strong when-to-use guidance: it warns that schema validation only catches syntax and will NOT find referential problems, steering agents toward using referential integrity as the primary/default check. It also explains the licensing situation (schema not bundled) so agents know they must supply their own copy. This gives clear usage context.

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