search_results

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

With no annotations, the description carries the full behavioral burden, and it does disclose two important traits: the operation is local-only (no network) and results are paginated. It omits what happens on an invalid or expired `search_id`, whether ordering across pages is stable, and any size/cost implications of the `records` view, which are meaningful for a paginated fetch.

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?

The text is short and front-loaded, with the core capability stated first and the two enumerated parameters set out as scannable lines. Every line does work; the only cost is that the extreme terseness leaves gaps that a slightly longer phrasing could close.

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 shapes need not be described, and the description covers the local/no-network model plus the two enumerated parameters. For a 5-parameter paginated read with zero annotation coverage it should still say something about `search_id` lifecycle and pagination interaction (limit/offset), which are the main ways an agent could misuse this tool.

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 0% across 5 parameters, so the description must compensate and it only partially does. It glosses `scope` values (selected/eligible/candidates) and lists `view` values (titles/compact/records) but never says what each view actually returns in terms of payload weight, and gives no meaning at all for `search_id`, `limit`, or `offset` beyond their self-evident names.

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?

The description states a specific verb and resource combination ('本地分页读取检索快照' - locally paginated read of a search snapshot) plus an operational constraint ('不联网' - no network). This clearly differentiates it from the sibling `search`/`structured_search` tools that presumably hit the network. It does not name those siblings explicitly, keeping it below a 5.

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?

The '不联网' (no network) clause and the required `search_id` imply this is the follow-up step to a prior search that materialized a snapshot, and the scope glosses hint at narrowing. However, there is no explicit statement of when to use this rather than re-running `search`, nor any exclusions or preconditions (e.g. snapshot expiry).

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