开始实时录制到磁盘

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

No annotations are provided, so the description carries the full burden, and it does disclose meaningful behavior: append-only JSONL with one event per line, memory-safe for long sessions, and ordered frame persistence. It omits overwrite/append semantics for pre-existing files and any permission requirements, leaving some gaps.

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, front-loaded sentences plus a short routing clause; the core behavior (append JSONL) leads, the secondary feature (frames) follows, and the hand-off to recording_stop closes it with no filler.

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 six-parameter, no-output-schema tool with no annotations, the description covers the essential mechanics and points to recording_stop for results. Remaining gaps are minor: file naming/collision behavior and concurrency expectations are not addressed, but the agent can call the tool 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 100%, so all six parameters (dir, name, rootDir, channels, saveFrames, performanceSampleMs) are already documented in the schema. The description only loosely gestures at channels and frames, adding no syntax or format detail beyond the schema, so the baseline 3 applies.

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 precise verb+resource: continuously appending the live event stream into a JSONL file, with optional ordered frame image saving. This is distinguishable from disk-unrelated siblings like events_subscribe or capture_start because the description emphasizes sustained disk-backed logging rather than one-off capture.

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?

Gives a clear usage context ('suitable for long-running monitoring without memory blowup') and names the terminating companion tool, recording_stop, for stats. It does not, however, state when to prefer this over capture_start or events_subscribe, so alternatives are left implicit.

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