find_similar_passages

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description goes well beyond them: it discloses the embedding-precondition on the input verse, the ranking by similarity score, and a substantial caveat about what the score cannot distinguish (quotation vs. allusion vs. shared tradition vs. coincidental overlap). That is exactly the kind of epistemic-limit disclosure annotations cannot carry.

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 purpose, then mechanism, then concrete worked examples, then the caveat. The four example pairs are illustrative and earn their space, but the passage is long and the caveat paragraph, while valuable, could be tightened without losing meaning.

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?

No output schema exists, yet the description conveys the return shape (passages ranked by similarity score), the mechanism, the precondition, and the interpretive limits of the score, plus where to go next. Nothing needed to call or correctly interpret this tool is missing.

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%, with 'reference' and 'limit' (default 10) both documented in the schema itself. The description adds the embedding requirement for 'reference', which is meaningful, but gives no guidance on how to choose 'limit' or what values are sensible. Baseline 3 applies when the schema does the heavy lifting.

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+resource ('Find passages with similar semantic content to a given Bible verse') and explicitly contrasts the mechanism with siblings: 'Matching is by vector embedding rather than shared vocabulary, so it surfaces connections that explicit cross-reference indexes and word searches miss.' An agent can distinguish it from get_cross_references and word_study without opening a schema.

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?

Establishes the precondition ('a verse reference with a pre-computed embedding') and routes the agent to follow-up tools (lookup_verse, get_study_notes, get_ane_context, get_cross_references) for interpreting results. It stops short of an explicit 'use this when / not when' rule against graph_enriched_search or find_connection, which are the closest conceptual alternatives.

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