search_records

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

Despite readOnlyHint=true already covering safety, the description adds substantial behavioral detail: default matching is fuzzy everywhere (results ranked, not filtered), wildcard rules, yearTolerance semantics (0 = exact, 1/2/5/10 = ±years, omit = fuzzy), and return behavior (up to 50 hits with indexed fields and ids). It also explains that collectionFocus re-ranks rather than filters, and that extraParams passes any other site query parameter. This goes well beyond what annotations provide.

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 long but every sentence carries necessary information. It is logically organized: purpose, input formats, matching behavior, event object details, wildcard rules, search strategy, special parameters, and return info. It front-loads the core purpose and progressively details advanced usage. There is no filler or redundancy.

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 tool with 32 parameters, nested objects, and no output schema, the description is remarkably complete. It explains how to construct effective searches, the meaning of key parameters, result size, and how results link to downstream tools (record.get, record.save_to_person). It also mentions related tools like record.suggest_places for gpid. The only missing detail is the exact JSON structure of the returned hits, but that's not required without an output schema and the description indicates the necessary information.

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 only 16%, so the description must compensate. It does: it explains name format ('First Last'), year format (4-digit), place format (free text with gpid), the cumulative matching levels for firstNameMatch/lastNameMatch, the structure and semantics of event objects (year, yearEnd, yearTolerance, place, gpid, placeScope), wildcard syntax and constraints, and the meaning of exactRelatives/exactKeyword/exactRace. It also covers collectionFocus, collectionId, and extraParams. Even though not every parameter is individually described, the ones needing explanation are covered thoroughly.

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 it searches Ancestry historical records (census, vital, military, immigration…) plus optionally trees, stories, and photos, and identifies it as the full website search form. This distinguishes it from siblings like record (which fetches a specific record) and person (which handles individual profiles). The scope is unambiguous.

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?

Provides explicit search strategy: 'Start broad (name + birth year), then narrow.' Explains when to use collectionFocus (re-rank toward a country/ethnicity) vs collectionId (restrict to one collection) vs extraParams (collection-specific fields). It also describes how to tighten matching per field (exactName, firstNameMatch/lastNameMatch, exactRelatives, etc.) and references downstream tools (record.get, record.save_to_person). This gives clear when-to-use and how-to-use guidance.

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