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

Beyond the readOnlyHint and idempotentHint annotations, the description reveals a critical limitation: it 'reads declared CSS and does not execute JavaScript' and reports 'what the stylesheets say rather than what the page renders.' This is valuable behavioral context that prevents false expectations and does not contradict the annotations.

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 front-loaded with the main verb and resource, and every sentence earns its place. The first sentence, however, packs a large 15-item output enumeration into one long clause, making it less scannable than a structured bulleted list would be.

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 one-parameter tool without an output schema, the description covers invocation, output scope, and the no-JavaScript caveat quite well. It does not explicitly state the exact return representation (e.g., Markdown text versus saved file) or behavior for inaccessible or CSS-less pages, so it is strong but not fully exhaustive.

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 schema already documents the only parameter with 100% coverage ('Absolute public http(s) URL of the page to read'). The description adds contextual emphasis that the target is a public site and that stylesheets are read, but it does not add new parameter-level semantics, so the baseline of 3 applies.

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 action and resource: 'Read the stylesheets of a public site and return a full DESIGN.md', and enumerates a detailed output list, so its purpose is unmistakable. However, it never references sibling tools like get_design_md or get_theme_tokens, so differentiation from close alternatives is implicit 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?

It gives a clear use context: 'This is the artefact to hand a coding agent before it writes UI that should match a site.' It does not mention when not to use it or point to alternatives such as get_design_md, so it lacks explicit exclusions and routing guidance.

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