trigger_crawl

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

No annotations are provided, so the description carries the full burden. It states the action (triggering a crawl) and optional persistence via save_to_local and include_url, which hints at resource consumption (saving to local, including URLs costs tokens). However, it doesn't disclose side effects like whether it creates data that other tools then read, how long the crawl takes, or if there are rate limits. It also doesn't mention that the operation might be blocking. It gives some behavioral detail (task status returned) but not comprehensive, so a 3 is fair.

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 but includes a clear summary, parameter explanations, return format, and examples in a structured format (Args/Returns/Examples). It's front-loaded with the purpose. It's not perfect because the parameter descriptions could be bulleted more cleanly, but it's efficient for a tool with 3 parameters. No wasted sentences, so a 4.

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 a trigger action with 3 params, an output schema (mentioned), and no annotations. The description covers the core functionality, parameter semantics, return type, and provides examples. It doesn't explain prerequisites like whether the crawl needs prior configuration or if it conflicts with scheduled crawling, but given the tool's simplicity and the output schema, it's reasonably complete. A 5 would need explicit note about side effects or dependencies, but a 4 is solid.

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 0%, so the description must explain parameters. It does: 'platforms' is described as a list of IDs with an example, 'save_to_local' is explained as saving to the output directory, and 'include_url' is explained as including URLs to save tokens. The examples also clarify usage patterns. This adds significant meaning beyond the schema's defaults and types, so a 4 is justified. A 5 would require more detail like accepted platform names or validation rules, but it's already strong.

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 clearly states the verb 'trigger' and the resource 'crawl' (爬取任务), and mentions optional persistence. It distinguishes from siblings like get_latest_news, get_latest_rss, and search_rss by being the tool that actually initiates a crawl rather than fetching or reading. However, it doesn't explicitly explain how it differs from other tools that might trigger similar actions, like sync_from_remote, so it doesn't reach a 5.

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 provides context on when to use it (manual trigger), but doesn't explicitly state when NOT to use it or mention alternatives. It gives examples and default behaviors, which helps the agent understand typical usage scenarios. Since it's a manual action in a set of read-centric tools, the need for explicit exclusions is less critical, so a 4 is appropriate.

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