sync_from_remote

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

With no annotations provided, the description must carry the behavioral disclosure burden, and it largely does. It explains that dates already present locally are skipped (skipped_dates), failed dates are reported with errors, and the operation requires specific S3 configuration. It does not explicitly warn about network load or whether it modifies existing files beyond skipping, but the skip behavior implies non-destructive sync.

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 well-structured with clear sections: overview, Args, Returns, Examples, and Note. Every section contributes necessary information — parameter semantics, return schema, usage examples, and configuration requirements — with no redundant filler. The purpose sentence 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 single-parameter tool, the description covers everything needed to invoke it correctly: parameter meaning and default, return format with all fields, configuration requirements, and usage examples. The output schema exists, but the description already details the return structure sufficiently, and the sibling context shows this is a standalone sync operation.

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 input schema only defines 'days' as an integer with default 7 and 0% description coverage. The tool description fully compensates by explaining the meaning ('pull data from the last N days'), enumerating common values (0, 7, 30) with concrete interpretations, and providing examples for both default and explicit usage.

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 opens with a specific verb and resource: '从远程存储拉取数据到本地' (pull data from remote storage to local), making the tool's core action unmistakable. It also situates the tool in the MCP Server workflow (crawlers store to remote cloud storage, server pulls for local analysis), which clearly distinguishes it from siblings like trigger_crawl, get_storage_status, or list_available_dates.

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 gives a clear usage context: pulling crawler data from remote cloud storage (e.g., Cloudflare R2) into local for analysis. It does not explicitly name alternative tools or state when-not-to-use conditions, but the scenario and prerequisites (config file or S3 environment variables) are clear enough for an agent to select it.

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