search_collections

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

Goes well beyond the readOnly/openWorld annotations by disclosing that FamilySearch offers no catalogue search, that this walks the catalogue in ~90-record page blocks, that the first call makes several API requests, that results are cached, and that refresh costs about ninety seconds. It also notes it works without a token, which is operationally important. Missing only response-shape details, though those are partly covered by the coverage-statement description.

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?

Front-loaded with the purpose and the payoff, with no filler sentences; every paragraph adds a usable fact (purpose, coverage reasoning, mechanics, auth). It is longer than strictly necessary and slightly essayistic, but the length is justified by the tool's non-obvious catalogue-walking behavior.

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 proactively explains what a result contains (a coverage statement: record types, place, years) and how to interpret it. Combined with the caching, paging, and auth notes, an agent has everything needed to call this correctly and reason about the 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?

Schema coverage is already 100%, so the baseline is 3, but the description adds real meaning: it clarifies that query words are matched against collection titles and that an empty query means browsing everything, which is more than the schema's 'leave empty to browse' phrasing conveys. The refresh/caching semantics are reinforced rather than merely repeated.

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 first sentence gives a specific verb (find) and resource (record collection) plus its downstream purpose ('so a search can be scoped to one'). It concretely distinguishes the tool from get_collection (fetch one by id) and search_records (search within one) by explaining the catalogue-walking match against titles.

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 states when to use it (once you know which collection should hold an entry, scope search_records to its id) and supplies the key prerequisite mental model: read the coverage statement, because a 1850-1900 collection cannot answer an 1840 question. It even distinguishes the meaning of a nil result depending on scoping.

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