graph_enriched_search

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

Annotations already declare readOnlyHint, destructiveHint, idempotentHint. Description adds behavioral context: it is comprehensive, works at verse-level only, and returns combined data. No contradictions, but no need for more since annotations cover safety.

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?

Description is structured with headings and examples, making it easy to scan. While slightly longer than minimal, every sentence adds value. It is front-loaded with the primary purpose.

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?

Given the tool has one parameter, no output schema, and high complexity in output (verse text, entities, relationships), the description fully explains what is returned and when to use it. It compares with siblings and provides a concrete example, making it complete for an AI agent.

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% (one parameter). Description adds value by explaining the parameter is a Bible verse reference, providing examples like 'Matthew 1:1' and showing how it translates into output. This goes beyond the schema's basic description.

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 that the tool is for deep study of a specific verse, returning verse text plus all people, places, events, and family relationships. It distinguishes itself from sibling tool 'people_in_passage' by specifying it is verse-level only and includes family relationships.

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 provides usage guidelines with 'USE THIS WHEN' and 'DIFFERENCE FROM' sections, telling when to use (deep-dive, sermon prep, saving calls) and when not to (use people_in_passage for chapters/entities only).

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