people_in_passage

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered by structured data. The description adds genuinely new context: the backing dataset, that scope can be a chapter or a single verse, and an illustrative example of what identities come back for two passages.

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?

Purpose is front-loaded in the first line, followed by data-source scope, examples, and sibling routing in that order. It is slightly longer than strictly needed — the two worked examples occupy most of the text — but each sentence still carries information an agent would use.

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 definition correctly compensates by describing what is returned and giving two concrete result sets, which is adequate for a one-parameter lookup. It omits a notable behavioral detail: passages with no tagged entities presumably return empty results, which an agent should know before treating an empty list as an error.

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 100% with a single documented 'reference' parameter, so baseline is 3. The description's examples (Genesis 22, Acts 15) reinforce the accepted reference format but add nothing the schema description does not already state.

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 ('List') and resource ('people, places, and events mentioned in a Bible passage') and names the data source (Theographic Bible Metadata). The concrete Genesis 22 and Acts 15 examples make the scope of output unmistakable and separate it from siblings like lookup_verse or explore_genealogy.

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?

'Relevant for establishing the cast and setting of a narrative passage' gives clear usage context, and it explicitly names graph_enriched_search as the related alternative with its distinguishing property (verse-level, adds verse text and family relationships). It stops short of stating when NOT to use it (e.g., non-narrative passages), so not a full 5.

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