search_records

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

No annotations, so the description carries the full behavioral burden and it delivers the non-obvious facts: limit is capped at 100, offset provides paging, and coverage gaps exist in the indexed registers. It does not state whether multiple filters are ANDed or how results are ordered, which are the remaining behavioral unknowns.

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 purpose sentence is front-loaded, the parameter lines are terse and scannable, and the caveat note is placed last where it matters most. Structurally efficient, though the parameter block is list-like enough that it reads as a schema restatement in places.

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?

An output schema exists, so return shape need not be described. What an agent needs to call it correctly, including the filter vocabulary, the 100-result cap, paging, and the regional-coverage caveat, is present. Only the filter-combination semantics and defaults are unstated.

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 0%, so the description must define all nine parameters and it does: text, name, place, the year bounds, only_digitised, limit/offset, and the full record_type vocabulary. It stops short of explaining how parameters combine and omits the default limit of 20 and default offset of 0.

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: 'Search Riksarkivet's catalogue and indexed registers.' That is concrete and distinguishable from siblings like get_register_record or get_page, though the only explicit sibling routing appears in the trailing note (parish_archive + get_page) and nothing distinguishes it from browse or volume_pages.

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 note gives an explicit when-not and alternative: indexed registers cover only some regions, so use parish_archive + get_page for church books elsewhere (e.g. Östergötland). It also says record_type can be omitted 'for everything.' It does not advise when to choose text vs name search, or when browse would be better.

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