抓取状态

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

With no annotations, the description carries the full behavioral burden. It discloses the inspected state (buffer count, target page, in-round flag), which implies a read-only probe, but never states explicitly that it has no side effects, nor whether it is scoped to the current session only.

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 front-loaded sentence covering all three returned facts with zero filler. Nothing redundant or misplaced.

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?

There is no output schema and no annotations, so the description must carry both the return-shape and safety burden. It names the three returned facts but does not describe the shape of the response (field names, units of the buffer count) or the non-mutating nature of the call.

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?

The tool takes zero parameters, so there is nothing for the description to clarify beyond the schema. Baseline 4 applies; the description correctly implies the call needs no arguments.

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 clear inspection purpose and enumerates exactly what is read: buffer count, target page, and whether a capture round is active. That is specific enough to distinguish it from capture_start/capture_stop, though it never names those siblings or session_info to disambiguate similar status reads.

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?

No when-to-use guidance, no prerequisites, and no reference to the sibling capture_start / capture_stop / capture_list_saved tools. The agent must infer that this is a non-mutating poll used before or during a capture round.

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