design_validate

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

With no annotations provided, the description carries the full burden and does well: it discloses that the tool performs an external API check against the standard, that it can operate over the entire user folder when both params are empty (broad-scope behavior), and that check_refs=false trades thoroughness for speed. It implies a non-destructive read/validation role, though it never states whether the tool writes or errors on failure.

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: one-line purpose, ★ key capability, parameter explanations, then a bulleted catch list. The final rhetorical sentence ('Trees are written by humans... fabricated clause numbers are the most dangerous') adds motivation but is functional padding rather than essential call-time information, keeping it from a 5.

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?

An output schema exists, so omitting the return format is acceptable. For a validation tool with an API dependency and five distinct detection categories, the description covers inputs, scope behavior, detection scope, and the external-check behavior. The remaining gap is the absence of explicit guidance on which sibling handles adjacent concerns and what happens on validation failure.

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 fully compensate — and it does. All three parameters (tree_yaml, path, check_refs) receive explicit semantics including the mutual-exclusivity relationship, the default behavior when both are empty, and the meaning of the boolean flag and its performance implication. This goes well beyond the bare schema fields.

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 states a specific verb+resource ('inspects a decision tree') and immediately front-loads the distinctive capability via ★: it verifies cited reference clauses actually exist by API call. The 'catches' list (missing schema, duplicate step identifiers, broken branches, fabricated clause numbers, design-method/standard mismatch) precisely distinguishes it from the design_* authoring siblings and kcsc_* retrieval tools.

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 gives useful in-tool usage guidance: the tradeoff between tree_yaml/path input (both empty → scans all user trees) and the check_refs speed toggle ('turn off = schema only, faster'). However, it never names alternatives or states when NOT to use this tool vs. a sibling (e.g., kcsc_audit or other design_* tools), leaving the selection decision implicit.

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