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

With readOnlyHint=true provided, the annotation already covers the safety profile. The description adds meaningful extra context: the screenshot is generated at build time, not on-demand, so it may be stale after a fresh publish. This is critical behavioral disclosure that prevents the agent from misattributing the screenshot's content. Lacks some detail on exact staleness timing but otherwise strong.

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?

Three short paragraphs, front-loaded with the core purpose in the first line, then useful caveats. Every sentence earns its place, with zero filler or repetition of schema/annotation content.

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 simple single-parameter read-only tool with a well-documented schema parameter and readOnlyHint annotation, the description fully covers purpose, usage context, timing caveats, and cost considerations. The inclusion of the cost/value warning is particularly thoughtful. No output schema needed given the tool's simplicity.

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% and the single 'project' parameter already has a detailed description explaining it accepts a slug or id and how to derive the slug (from my_projects). The tool description doesn't add anything beyond the schema, which aligns with the baseline 3 for high coverage single-parameter tools.

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 clearly states the tool shows the last built version of the site as it looks visually. It distinguishes from siblings by explicitly naming read_site (content) and site_issues (problems), establishing this tool answers the third question: appearance. The verb+resource+scope is specific and differentiating.

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 description explicitly states when to use it (before/after visual editing) and gives concrete exclusions: don't call aimlessly, and notably warns not to pass off a stale screenshot as the result of one's own edits after publishing. It also directs users to site_issues as the cheaper, more specific alternative for diagnosing problems. This is exemplary guidance.

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