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

Annotations already cover read-only, idempotent, open-world, non-destructive, so the bar is lower; the description still adds non-obvious behavior — that the query may be rewritten via the configured AI provider, which can affect results, and that responses include fetch dates and collection status. It does not mention latency or cost implications of that provider call.

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?

Four short sentences, front-loaded with purpose before return shape and routing. The limit sentence duplicates the schema description and could be dropped without loss.

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 values need not be enumerated; annotations carry the safety profile. The description supplies the remaining essentials: scope, result shape, query translation caveat, and the handoff to knowledge.read.

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 both parameters are already fully documented, including limit defaults and bounds. The description's 'Limit sets the maximum number of sections' merely restates the schema and adds no new semantics for query either.

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 (search) and resource (saved hotel website text), plus the input modality (question or topic). It explicitly distinguishes itself from knowledge.read, which is the natural sibling to confuse it with.

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 follow-up routing rule: 'Use knowledge.read with a returned pageId to read the full saved page.' That is clear context for the search-then-read flow, but there is no guidance on when search is inappropriate (e.g., fetching a known page directly).

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