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

Annotations already establish readOnly/not-destructive/closed-world, so the safety profile is covered. The description adds real behavioral context by explaining what each invocation mode yields: with `section`, a worked example with fields, render tree, and CSS; with `reference`, the developer-docs reference broken into components/scopes/data. This goes beyond the annotations without contradicting them.

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?

Front-loads the core purpose, then explains modes and the pre-design invocation rule. It is longer than most tool descriptions but each sentence carries information (what it covers, when to call it, what each param returns). Slight redundancy around the "read it before" framing but overall 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 read-only, no-output-schema tool with two optional documented parameters, the description is complete: it covers purpose, trigger timing, and the return shape per mode. An agent has everything needed to decide to call it and how to invoke it.

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 coverage is 100%, so the baseline is 3, but the description meaningfully expands on both parameters: it clarifies that `section` returns a full worked definition (fields, render tree, CSS) and that `reference` accepts components, scopes, data, or a single component name. This adds semantic value beyond the schema's own descriptions.

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?

States a specific resource (the design guide) and enumerates exactly what it covers: pages, header/footer, sections, themes, and the layout language (node types, expressions, components, CSS rules). It ties itself to the broader workflow by naming define_section and theme files as the things written in this language, distinguishing it from sibling tools like define_section and list_section_types.

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?

"Call it once before designing anything" and "Read it before deciding something cannot be done" give clear timing and trigger conditions. It does not name a competing alternative to route away from, but the placement advice (call first, call before designing) is strong, actionable guidance.

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