trigger_crawl

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

With no annotations, the description carries the disclosure burden and does a good job: it reveals that this is a manual/mutating crawl action, that persistence is optional via save_to_local, that include_url=False saves tokens, and that the return is JSON task status with success/failure platform lists. It does not cover rate limits, duration, or whether the crawl may overwrite existing data, but it provides materially more than a bare mutation label.

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?

The description is compact and well-structured: a one-line summary, labeled Args with defaults/meaning, a Returns note, and two concrete examples. No redundant filler appears, and the key scoping behavior (default all platforms) is front-loaded.

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 three-parameter tool with an output schema and clear examples, the description covers invocation, defaults, and return shape sufficiently. It could be even more complete by noting whether the crawl runs synchronously/asynchronously and how invalid platform IDs are handled, but nothing an agent strictly needs to call it correctly is missing.

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 coverage is 0%, so the description must document parameters, and it does: platforms is explained with domain examples and a default ('use all platforms'), save_to_local is tied to the output directory, and include_url is explained with a token-saving rationale. This adds real semantic meaning beyond the raw JSON schema.

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 opening line states a specific verb and resource: '手动触发一次爬取任务' (manually trigger a crawl task), with optional persistence. This clearly identifies it as the direct crawl-trigger action and distinguishes it from the read/analysis tools among its siblings.

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?

The description implies usage by explaining default behavior (all platforms when platforms is unspecified) and providing two examples, but it never explicitly says when to choose this tool over alternatives. No exclusions or 'use X instead' guidance is given, though the manual-trigger wording makes the basic intent reasonably inferable.

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