收回一条低语。树洞会放人收回说过的话（洞主可用 HOLLOW_FORGET=off 关闭收回）。
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"whisper_id": "<whisper_id>"
},
"name": "forget"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| whisper_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description must cover the destructive behavior itself. It usefully states that retraction may be unavailable if the hole owner sets HOLLOW_FORGET=off, which is a real operational caveat. It does not say whether retraction is permanent, whether replies or traces remain, or what error occurs when the feature is disabled.
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?
Two short sentences, front-loaded with the action, then the availability caveat. Nothing is padded, though the parenthetical about the hole owner's switch is slightly cryptic.
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 don't need explaining. For a destructive, unannotated single-parameter tool, though, the description omits the permission model and reversibility, which an agent needs before calling it.
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?
There is a single parameter, whisper_id, with 0% schema description coverage, and the description only implies that it identifies the whisper to retract. It adds no format, provenance, or ownership semantics beyond the target noun.
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: 收回 (retract) a 低语 (whisper). That makes the operation clearly distinct from the sibling 'whisper' (presumably for posting one), although it never names that sibling explicitly.
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 phrase 收回说过的话 implies the use case is undoing a whisper you have already posted, but the description never states the prerequisite (authorship or ownership of the whisper) or what to do when retraction is disabled; it only notes that the hole owner can turn the feature off.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.