douyin_local_check

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

Annotations carry only a title, no readOnlyHint/destructiveHint, so the description must signal side effects — it does so implicitly by describing measurement and a problem list, which reads as a local, non-mutating inspection. It adds useful context about the return content (问题清单) and the optional frame grab, but omits file-access constraints, supported container/codec limits, and failure behavior on unreadable files.

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 purpose and the checklist, no filler. The telegraphic enumeration is dense but appropriate; nothing is wasted, though the phrasing is clipped enough that the frame-extraction clause reads as an afterthought.

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 simple two-parameter, non-mutating tool with no output schema, the description covers what is checked and what comes back (a problem list, optionally a frame). The main remaining gap is the missing disambiguation from douyin_publish_preflight, which matters given how many publish-related siblings exist.

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 both parameters are already documented and the baseline is 3. The phrase "顺便抽一帧看画面" adds a hint that frameAt is a secondary, optional convenience rather than part of the core check, which is modest added meaning.

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 names a specific verb (自查/pre-publish check) and resource (local video file), and enumerates exactly what is measured: duration, resolution, aspect ratio, audio track presence, bitrate, size, plus a problem list. However, it never distinguishes itself from the sibling douyin_publish_preflight, which by name covers the same pre-publish validation territory, so an agent cannot cleanly choose between them from the description alone.

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?

"发布前自查" implies the timing (before publishing) but gives no explicit when-not guidance, no prerequisites, and no mention of the alternative douyin_publish_preflight or douyin_breakdown. Usage is inferable rather than stated.

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