shop_page

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

With no annotations, the description carries the whole disclosure burden and does so thoroughly: it reveals file saving, module-cache invalidation, the markup-not-picture caveat, POST side effects on database and email, session-cookie persistence for POST sequences, fresh-visit behavior for plain reads, and the debug parser report. This is exceptionally candid about effects an agent cannot infer from the schema.

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 dense but well-ordered: action, save location, output shape, then caveats. It avoids repeating schema text, though phrases like 'the rest is cleared by hand' and the run-on sentence structure make it slightly harder to parse than necessary.

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?

Given no annotations and no output schema, the description is remarkably complete: it explains return content, file persistence, side effects, session behavior, debug output, and the practical meaning of markup versus visual appearance. An agent has enough context to invoke the tool safely and interpret its results.

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 find, path, and post, so the description doesn't need to restate them. It adds crucial semantics by explaining that post changes a read into a visitor-submitted form with real store side effects and cookie persistence, and it provides the only explanation of the otherwise undocumented debug parameter. This meaningfully exceeds the schema baseline.

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 the operation precisely: fetch a store page as a visitor sees it, save the HTML under mcp/melbis/pages/, and answer with status, size, title, and either matching fragments or the page head. This clearly separates it from sibling engine_* and shop_download tools by emphasizing the rendered visitor view, file save, and summary output.

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 gives clear contextual guidance: use it for visitor-visible storefront pages, and use POSTs to drive storefront flows like filling a basket or writing a review. It also warns when to avoid POST without owner consent, though it never names an alternative tool or gives an explicit 'when not to use this' condition.

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