tail sessions

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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world scope, so the safety profile is covered. The description adds almost nothing beyond that: it does not say how "最近" is ordered (last activity vs creation), whether tails are truncated, what the result shape is, or what "快速" costs relative to a full read. Only the lightweight-sampling intent is new information.

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?

One short sentence, front-loaded with the action and immediately followed by the use case; no filler. It is arguably over-terse for the amount of ambiguity it leaves, but nothing in it is wasted.

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?

The tool is simple (2 optional parameters with defaults, no output schema, full annotation coverage), so most of the burden is already carried by structured fields. However, an agent still cannot tell from the description how sessions are ranked as "recent" or whether the tails are complete messages or truncated previews, which matters for a sampling tool. Adequate but with a clear gap.

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 100% (count = 会话数, perSession = 每会话消息数) with defaults, min and max all declared, so the schema does the heavy lifting. The description's "N 个会话" and "末尾消息" merely restate those parameters at a high level and add no format, ordering, or edge-case semantics. Baseline 3 is the right level.

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?

"快速采样最近 N 个会话的末尾消息" names a specific verb (采样), a specific resource (会话末尾消息), and a scope (最近 N 个). An agent can distinguish this tail-sampling operation from minimax_read_session or minimax_list_sessions. It stops short of 5 because it never names a sibling or states the distinction 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?

"用于并发任务巡检" gives one concrete usage scenario, which is real context, but there is no statement of when to prefer this over minimax_read_session / minimax_list_sessions / minimax_pending, nor any exclusion. Usage is implied rather than specified.

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