source_add

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

With no annotations provided, the description carries the full burden of behavioral disclosure and meets it admirably. It discloses that admission does not guarantee provider processing success, notes that file paths are relative to the MCP server machine, explains the impact of the 'wait' parameter, and mentions that image sources may feed video generation pipelines. These details go beyond simple parameter lists.

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-organized with a synopsis, parameter list, and examples, making it easy to scan. However, the omission of the 43 file extensions (or moving them to an external reference) would improve conciseness without losing critical operational detail. The structure itself is strong, but the length borders on excessive for an MCP tool description.

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 the high complexity (11 parameters, 4 source types, async behavior), the description is remarkably complete. It covers edge cases like bulk uploads, server-side file paths, wait timeouts, and provider processing caveats. Since an output schema exists in the structured data, the omission of return value details is acceptable, and the description fully supports the agent in a wide range of usage scenarios.

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 fully compensate, which it does. Every parameter is documented with its purpose, allowed values (like source_type options), and behavioral implications (e.g., url vs urls mutual exclusivity, file_path accessibility, wait_timeout default). The examples further illustrate parameter usage in context, making the schema far more usable.

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 'Add a source to a notebook. Unified tool for all source types,' which uses a specific verb and resource while clearly stating its role as the consolidated tool. This differentiates it from specialized sibling tools like source_delete, source_rename, and source_describe, which are all listed alongside it.

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 clear usage context for each source type (url, text, drive, file) and includes multiple examples demonstrating single vs bulk URLs, wait behavior, and file usage. It implicitly excludes non-add operations, though it does not explicitly name alternative tools for other operations. The guidance that 'a path on a different client/agent host is not accessible' is a valuable caveat.

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