Lint recipe library

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

Beyond the annotations (readOnlyHint=true, destructiveHint=false), the description adds critical behavioral details: it states 'never calls TouchDesigner' (no external side effects) and 'Returns a structured report' (output format). It also lists the exact rules checked, providing transparency about what the tool validates. This adds value beyond the annotations and sets expectations for safe, offline execution.

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 compact, with the first sentence stating the core purpose and the second listing the checks. While the second sentence is long, every item is necessary to convey scope. It is front-loaded with 'Offline semantic linter' and ends with a state guarantee. The structure is acceptable but could be improved by breaking the rule list into a more scannable format.

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 description covers the tool's function and key behavioral traits, but it does not describe the structure of the returned report (e.g., list of issues with severity levels). Although the schema-parameter descriptions explain fail_on and severity, the actual report format remains vague. Given there is no output schema, the description should have elaborated on what the 'structured report' contains for a complete understanding.

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?

The input schema has 100% coverage: every parameter (rules, fail_on, severity, recipe_id) includes a description with defaults and enums. The tool description itself does not add parameter-level details, but since the schema is thorough, it meets the baseline. No additional compensation is needed.

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 identifies the tool as an 'Offline semantic linter for recipes/*.json' and enumerates the specific checks it performs (schema, id/filename match, duplicate node names, etc.). It uses a specific verb ('lints') and resource ('recipes/*.json'), and distinguishes itself from siblings by emphasizing offline operation and never calling TouchDesigner.

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 provides clear context for when to use the tool: it is offline, never calls TouchDesigner, and runs a set of semantic checks on recipe files. However, it does not explicitly name alternative tools or state when not to use it (e.g., 'use validate_recipe_bundle for schema-only validation'). The 'never calls TouchDesigner' hint implies a safe offline choice but lacks explicit comparison to siblings.

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