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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description's contribution is pagination semantics: results are chunked and must be reassembled from an offset. That is genuinely useful behavior not expressed by annotations. It stops short of explaining how the agent detects the end of content or whether truncation is signalled.

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?

A single sentence, front-loaded with the return value and the paging constraint, then the intent. No filler or restatement of the title.

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 carries the burden of describing the return shape, and it only says 'HTML one page at a time' without saying whether the response is a bare string, an object, or whether it reports remaining length. For a paginated read tool this leaves a real gap in knowing when to stop paging.

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 75% and the schema itself documents design (1-3), offset (default 0), and maxChars (default 20000, max 40000). The description reinforces the offset/paging model but adds no format or boundary detail beyond the schema, and projectId remains undocumented in both places. 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 states a specific verb and resource ('Returns a finished design's HTML') and adds scope ('one page of text at a time, starting at offset'). It implicitly contrasts with get_designs by emphasizing finished HTML rather than metadata, but it never names a sibling, so the differentiation is inferred rather than explicit.

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 phrase 'for building the design in another codebase' gives a concrete use case, which is more than most definitions offer. However, it gives no when-not guidance and does not route the agent to get_designs for metadata or edit_design for changes, leaving the sibling choice to inference.

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