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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so safety is covered. The description adds genuinely non-structured behavior: matching is semantic ('closest in meaning') rather than keyword, it spans all of the reader's books, and results carry a 0–1 similarity score. It omits cost/latency expectations for an embedding-style search, but the semantic-matching trait is the key behavioral disclosure.

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 and scope, followed by the when-to-use and id-provenance sentence, then concrete examples. The opening sentence is dense and front-loads return fields that the output schema already covers, but no sentence is filler and the examples earn their place.

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?

An output schema exists, so the description does not need to detail the response, and all four parameters are schema-documented. Combined with the explicit trigger and id-source routing, an agent has everything needed to call this correctly without further inference.

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% and every parameter (id, type, limit, threshold) is documented, including defaults and max, so baseline 3 applies. The description adds only the id-provenance mapping (quote id from list_saved_quotes, note id from get_reading_notes) and two call examples, which largely restate the schema rather than adding new semantics.

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 and resource — 'finds the quotes and notes... closest in meaning to one of their saved quotes or notes' — plus scope ('across all their books') and the result shape (book, author, page, similarity score). An agent can distinguish this semantic-similarity lookup over the reader's own collection from search_book_content or get_passages_near_reading_position 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?

Gives an explicit trigger ('Use when the reader asks what else they have saved that connects to a particular quote or note') and names the prerequisite source tools: list_saved_quotes for a quote id, get_reading_notes for a note id. It stops short of stating when NOT to use it or contrasting it with the closest sibling, get_passages_near_reading_position, so it lacks full exclusion guidance.

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