Download a doc’s images

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

With no annotations provided, the description must disclose behavior itself. It mentions the return mapping (objectId→filename), which is valuable, and notes the correlation with read_doc markers. However, it omits potential side effects such as folder creation (though mentioned in the schema), file overwriting behavior, handling of tabs or accounts, and error cases (e.g., no images). This is adequate but leaves gaps in behavioral exposure.

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 two sentences long, with the first sentence stating the primary action and the second providing crucial context about the return value and its relationship to read_doc. There is no redundant information or fluff. The structure is front-loaded and every clause earns its place.

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 no output schema, the description sufficiently explains the return value (objectId→filename mapping) and its purpose. It addresses the main use case and integrates with read_doc. However, it does not clarify behavior across tabs (a parameter in the schema) or mention edge cases like empty documents or duplicate filenames. This is a minor gap, so it earns a 4 rather than a 5.

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 describes 3 of 4 parameters (dir, tab, account) with documentId lacking a description, giving 75% coverage. The tool description adds contextual value by explaining the mapping output and the relationship to read_doc, which helps understand the purpose of documentId and dir. However, it does not add specific parameter-level syntax or format details beyond the schema, so the baseline of 3 is appropriate.

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's function: 'Download every embedded image in a Google Doc to a local folder.' It specifies the action (download), the resource (embedded images in a Google Doc), and the destination (local folder). It also distinguishes itself from related tools by noting the correlation with read_doc's markers and describes itself as 'the inverse of publishing,' which differentiates it from image insertion or viewing tools.

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: when you need to download images and rewrite read_doc's image markers to local paths. It implicitly suggests using this tool in a workflow with read_doc, but it does not explicitly state when not to use it or name alternative tools. There is no exclusion criteria or comparison to siblings, so it earns a 4 rather than a 5.

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