search_passages

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

With no annotations, the description carries the full burden and does so: it discloses the transport ("RPC-backed (no browser)"), the absence of side effects on quotas ("no generation quota is spent"), and the shape of what comes back ("the indexed text with its offsets"). These are exactly the non-obvious traits an agent cannot infer from the schema.

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 sentences, each earning its place: what it does, what it is not, and when to pick it over the alternative. The ordering guarantee and the retrieval-not-generation claim are both front-loaded.

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 return-shape explanation is unnecessary, and the description still adds the one thing the schema can't: that no generation quota is consumed. For a 6-parameter search tool behind an RPC transport, nothing an agent needs in order to call it correctly 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%, including non-obvious semantics like source_names erroring on ambiguity and limit being omittable, so the schema already does the heavy lifting. The description adds only the ranking direction ("best first") and nothing about notebook_id vs notebook_url resolution or scoping behavior. Baseline 3 is appropriate.

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 the passages in a notebook's sources that match a query") plus the ordering guarantee ("ranked best first"). The phrase "This is retrieval, not an answer" immediately separates it from generation siblings, so an agent can classify the tool 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?

Explicitly names the alternative and the condition that selects it: "Prefer this over ask_question when you want the evidence rather than the prose, and when you intend to reason over the passages yourself." That is a genuine when-to-use rule. Minor deduction because the referenced name "ask_question" does not appear in the sibling list (the actual sibling is notebook_ask), so the routing pointer is slightly harder to follow than intended.

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