Crawls all pages under a RID read-only to return each page's fields and repeat groups, helping you map which Kennzahl belongs to which form page.
Walks every page below a RID (breadth-first, read-only) and returns each page's fields and repeat groups. Use it once per form/Anlage to learn which Kennzahl lives on which page.
| Name | Required | Description | Default |
|---|---|---|---|
| rootRid | Yes | ||
| maxPages | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose read-only status, breadth-first ordering, and that it is intended as a one-time discovery pass. It omits cost/truncation behavior (what happens at the default maxPages=60), pagination, and any error handling for an operationally heavy crawl.
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?
Two tight sentences, front-loaded with the core action and finishing with the usage cue. No 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?
No output schema and no annotations, so the description must cover behavior and returns. It names what is returned (fields, repeat groups) but leaves the maxPages cap and truncation semantics unexplained for what is a potentially expensive crawl.
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 0% and neither parameter is documented in the schema. 'Below a RID' gives partial meaning to rootRid, but maxPages (default 60) is never explained — an agent cannot tell what the page cap means or how it affects results.
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?
Specific verb ('Walks every page below a RID') plus the traversal order (breadth-first, read-only) and the return content (fields and repeat groups). It implicitly contrasts with single-page siblings like elster_form_page by emphasizing 'every page', but it never names a sibling, so it stops short of full discrimination.
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?
'Use it once per form/Anlage to learn which Kennzahl lives on which page' gives a clear context and even a quantity hint ('once'). However, it does not name alternatives (e.g., elster_kennziffern_list, elster_form_page) or state when not to crawl.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.