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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is procedural: it discloses that the return is a file to be saved verbatim and that the agent should work from the saved file rather than the response. It does not mention size limits, truncation, or what happens for an unindexed site, which are the remaining behavioral gaps.

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-loaded with the usage trigger and the core instruction, and nearly every clause carries information. It is dense with nested quotes and parentheticals, which slightly hurts scanability, but no sentence is filler.

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?

There is no output schema, so the description must characterize the return value — and it does, describing a verbatim text file in one of three known formats plus the instruction to persist it. For a two-parameter read tool with full annotation coverage this is close to complete, with only edge-case behavior (invalid site, large outputs) unaddressed.

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 earns above baseline by explaining what each of the three enum values actually produces rather than just naming them — meaningful semantics the schema's "Which file to return" does not convey. The site parameter's accepted forms (slug/URL/brand) are left entirely to the schema.

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 verb and resource (returns a design file for implementation) and immediately enumerates the three concrete output formats with what each contains (YAML tokens + prose, CSS custom properties, Tailwind v4 @theme block). It also explicitly distinguishes itself from get_site and get_design, so an agent can tell it apart from siblings without opening schemas.

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?

Gives an explicit positive trigger ("Use this when you will implement from a site's design") and an explicit negative case with named alternatives ("Not for answering questions about a site (use get_site or get_design)"). Both the use and the do-not-use routing are stated, leaving nothing to inference.

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