Mechanics that apply to the PAGE, not to a section

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

With no annotations, the description carries full responsibility for behavioral disclosure. It reveals that some kinds return a 'not-a-component' verdict instead of a candidate list, that treatments add on top without consuming sections, and that they compete for capabilities like scroll owner and document height. This goes beyond basic description to expose important edge-case behavior.

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 somewhat long but every sentence provides valuable context: purpose, historical rationale, behavioral exceptions, and integration guidance. It is front-loaded with the key distinction from suggest_mechanics. Slightly verbose due to the historical aside, but still efficient.

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?

For a tool with no output schema and no annotations, the description covers purpose, scope, behavior, and integration requirements comprehensively. It explains the conceptual model (page vs section), constraints (not consuming sections, not counting toward motion_coverage), and special output types. An agent has enough information to select and invoke this tool correctly.

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 provides 100% coverage with descriptions for all parameters. The description adds some high-level context (e.g., scroll-suave is a decision rather than a component), but it does not need to explain parameters since the schema already does. Baseline 3 is appropriate.

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 explicitly states it is 'The twin of suggest_mechanics for the family that does not fill a section slot' and lists concrete page-level treatments (smooth scroll, shaped edge, page background, custom cursor, route transitions). This clearly identifies the tool's function and differentiates it from the sibling suggest_mechanics.

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?

It names the sibling tool as an alternative and clarifies the scope (page-level vs section-level). It also provides specific guidance: 'A treatment does NOT consume a section and does NOT count toward motion_coverage' and advises passing adopted treatments to get_integration_contract, giving the agent concrete when-to-use context.

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