Filter messages in a chat session by exact sender ID within a bounded window. Returns scanned count, cursor, and coverage boundaries, avoiding nickname mismatches.
在一个会话的有界消息窗口中按发送者ID精确筛选；返回扫描数、游标和覆盖边界。不会把昵称相似当同一人。
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| offset | No | ||
| end_time | No | ||
| sender_id | Yes | ||
| scan_limit | No | ||
| session_id | Yes | ||
| start_time | No |
Changes observed during successful MCP inspections.
v4.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds value beyond them by disclosing the return shape (scan count, cursor, coverage boundaries) and the bounded-window scope consistent with openWorldHint=false. The exact-match-not-nickname caveat further discloses behavior. No contradiction with annotations.
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 dense sentences with zero filler. The primary action is front-loaded, followed by the return disclosure and a single high-value caveat. Every clause earns its place.
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?
With no output schema and 0% schema coverage, the description carries the full burden. It conveys purpose, return format, and matching semantics, but leaves pagination parameters (limit/offset), scan_limit semantics, and time-window conventions to inference — a real gap for a 7-parameter tool an agent must invoke correctly.
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%, so the description must compensate — and it does partially, explaining the core semantics (sender_id exact filter, bounded window) and hinting at scan_limit/offset via 'scan count' and 'cursor'. But it leaves limit, start_time, end_time, and the precise meaning of coverage boundaries unexplained across 7 parameters, falling short of full compensation.
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+resource (precisely filter messages by sender ID) within a clearly bounded scope (bounded window of a session). The nickname caveat ('不会把昵称相似当同一人') sharpens its identity against fuzzy-search siblings like search_messages, making the tool's exact-match purpose unmistakable.
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?
Usage is implied by the precise-filter semantics — an agent can infer it is for exact sender-ID lookups rather than fuzzy search — but the description never names alternatives or states when not to use it. With 38 siblings including search_messages, get_recent_messages, and extract_person_messages, explicit routing would materially help.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.