validate_scene

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

With no annotations, the description carries the full burden. It clearly discloses that the tool does not render (side-effect-free validation), states the exact return shape, and reveals behavioral nuances like default orientation (portrait) and auto-flipping of layouts. It could go further by disclosing potential errors or side effects, but for a validation-only tool this is sufficient.

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?

Though the description is long, it is well-structured and front-loaded with the core purpose and return type, followed by actionable guidance. Every sentence earns its place by providing decision rules (track kinds, orientation, list_examples) or clarifying behavior. No fluff or tautology.

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 is complex (nested schema, multiple track kinds), but the description covers all essential context: what the tool does, when to use it, how to choose track kinds, how to get canonical examples, and supported orientations. It also mentions the return shape, which is sufficient given no output schema. The guidance to call list_examples fills potential gaps in schema 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% description coverage, so the baseline is 3. The tool description adds value by explaining how to choose the track 'kind' based on content shape (flow, hub, comparison, etc.) and how orientation affects layout, which goes beyond the schema's field-level definitions. This extra guidance materially improves an agent's ability to construct a valid spec.

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 opens with a specific verb+resource: 'Validate a scene spec against the schema without rendering.' It also defines the return shape (`Returns { ok, errors? }`) and explicitly distinguishes itself from the sibling `render_scene` by stating it is for checking structure before rendering, making its purpose unambiguous.

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 explicit when-to-use guidance: 'Useful to check structure before render_scene.' It then gives detailed instructions on choosing track kinds based on content shape, including 'Do not reach for list-reveal unless...' and 'Use flow when...' for each relevant kind. It also instructs to 'Call list_examples first' and clarifies orientation options, fully covering usage alternatives.

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