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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so safety needs no restating. The description adds genuinely new behavior: results include a verbatim quoted passage only when one actually answers the question, plus notes matching the topic and passages close in meaning, each carrying a URL — revealing a hybrid lexical+semantic retrieval model and that indexing is limited to published content.

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?

Three short sentences, front-loaded with the purpose followed by return shape and the scoping hint. Every sentence carries information, though the return-shape sentence is dense enough that an agent may need to re-read it.

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 compensates by describing the result structure and URLs; parameters are fully covered by the schema. Minor gaps remain — whether limit applies to notes only versus passages, and what an empty result looks like — but nothing blocking for coherent invocation.

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%, so the schema documents slug format, limit bounds, and query length; baseline is 3. The description adds only slight extra meaning by explaining that the note parameter scopes the search to a single note rather than just naming the slug — useful effect-level context but not enough to exceed the baseline.

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 — find published passages that answer a question — and enumerates the three result kinds (best verbatim passage, covering notes, semantically close passages). It never names a sibling, though 'search inside one note' implicitly contrasts with get_note, so differentiation is left partly to inference.

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?

'Find the published passages that answer a question' implies the triggering condition (a natural-language question), and 'Give note to search inside one note' explains the narrowing case. But there is no explicit when-not guidance and no routing to get_note for full-note reads or latest_notes for browsing, which an agent needs to choose correctly among five siblings.

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