share_files

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

The description fully discloses the required workflow, including that preview returns a confirmationToken needed for download, that read returns inline content without a link, and that metadata must be presented to the user for approval. This is comprehensive given the absence of annotations.

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 and well-structured, using a clear bullet-like format with each action on its own line and key instructions highlighted. Every sentence provides essential information without redundancy.

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 description covers all necessary behavioral details for the tool, including return types for each action (inline for read, metadata+token for preview, public link for download) and the critical workflow dependency. No output schema is needed given this clarity.

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?

With 100% schema coverage, the baseline is 3. The description adds significant value by explaining the enum values in detail (e.g., read vs preview vs download) and the dependency on confirmationToken, which is not fully captured by the schema alone.

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 reads or shares workspace files and explicitly lists three distinct actions (read, preview, download), each with a specific purpose. It also distinguishes itself from sibling tools like download_from_url and web_search by being scoped to workspace files.

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 explicit guidance on when to use each action, including the mandatory order: preview before download. It also warns against skipping the preview step. However, it does not explicitly state when not to use this tool or compare directly with siblings.

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