trigger_crawl

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

With no annotations, the description must disclose side effects, but it only mentions optional persistence and return of task status. It omits details on data overwrites, network usage, duration, cancellation, or permissions. This is insufficient for safe agent use.

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 concise with sections for purpose, args, returns, and examples. No redundant sentences. The use of Chinese in the intro may slightly hinder global readability but does not reduce structural quality.

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?

Given an output schema exists and sibling tools are available, the description covers parameters and return format adequately. However, operational context (e.g., how long a crawl takes, concurrency limits) is missing, making it just adequate for a moderately complex action.

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 description adds meaningful explanations for all three parameters: platforms (list of IDs), save_to_local (boolean for output directory), include_url (boolean for URL inclusion). Since the schema has 0% description coverage, this added value is significant and clear.

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 tool triggers a manual crawl task with optional persistence. It lists parameters and examples, making the purpose evident. However, it could be more explicit about what 'crawl' means in context (e.g., data source) to distinguish from similar tools like get_latest_news.

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 explicit guidance is provided on when to use this tool versus siblings like sync_from_remote or get_latest_news. The examples show basic usage but do not explain scenarios where manual triggering is appropriate or preferable.

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