rlp_search

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

Annotations cover read-only and open-world status, but the description adds real value beyond them: the shape of each result unit (signature, title, years, permalink), the crucial caveat that a unit is a finding aid rather than the record, and the guidance that zero hits may reflect filing by Bürgermeisterei/Standesamt. These are interpretive behaviors the annotations cannot convey.

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 core purpose is front-loaded in the first sentence, and the trailing clauses each add distinct facts (collection coverage, result fields, finding-aid caveat, filing convention). The line-wrapped format is slightly awkward but no sentence is 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?

With no output schema, the description does the necessary work of naming the returned fields and clarifying that hits are finding aids rather than records, and pagination semantics are covered in the schema. An agent could call this correctly; only the absence of explicit exclusion conditions keeps it below a 5.

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 description coverage is 100%, so place, year_from/year_to, register, page, and rows are already documented with examples and defaults. The description reinforces that 'place' may be a Bürgermeisterei or Standesamt rather than a modern municipality, but this is largely restated in the schema's place description, so it adds only marginal meaning.

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 a specific verb and resource: 'Find the digitised civil registers of a Rhineland-Palatinate place in APERTUS', scoped to a named archive and collection. It also distinguishes itself from the sibling rlp_image ('read a page with rlp_image'), so the agent can tell which of the two to call.

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?

Explicitly routes page-reading to rlp_image and warns that 'a zero is not a negative' because registers are filed by Bürgermeisterei or Standesamt, which tells the agent how to interpret empty results. It lacks an explicit statement of when NOT to use it (e.g., non-Rhineland-Palatinate places), but the geographic and date scope ('mostly the state's north, from 1798') implicitly bounds usage.

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