调整检索边界（逃生口）

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

With no annotations, the description carries the full burden. It usefully discloses that mode "full" disables clipping and that privacy ignores are never bypassed, which is real behavioral context. It does not disclose the persistence model of the new scope (per-connection? until reset?) or whether it is a mutating call, which matters for a state-changing tool.

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?

A single compact sentence, front-loaded with the triggering situation before the two actions it performs. Nothing is padded, though the terseness borders on cryptic for a tool with an unexplained enum member.

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?

For a 3-parameter, nested-object, unannotated, output-schema-less tool, the description covers purpose and the key privacy invariant but leaves the mode enum and filter semantics under-described. An agent could call it but would likely guess at 'predicate' mode.

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 only 33%, so the description must compensate. It explains only the 'full' enum value; the 'predicate' mode is left undefined, and the six filter sub-fields are summarized merely as '新过滤条件' without semantics such as date format for since/until or what files/sources accept. Partial compensation for a low-coverage schema.

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 identifies the tool as a relaxation/escape-hatch for retrieval scope, with two concrete effects: mode "full" removes clipping, or new filter conditions are set. That is a specific verb+resource, though it never plainly says 'this sets the scope used by subsequent searches', leaving the agent to infer the resource from the name and title.

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?

'收得太紧时的放宽通道' gives a clear triggering condition: use it when results are being over-trimmed. It also names a hard exclusion ('隐私 ignore 永不受影响'), but it does not point to any sibling (e.g. search_sessions) as the alternative when the scope is already fine.

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