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

Beyond the annotations (readOnlyHint=false, idempotentHint=false), the description discloses the highest-value behavioral facts: the link is single-use and expires in 15 minutes, the payload is a zip of the folder's full subtree, and downloading draws against the account's monthly export row quota. It also states a scope limitation (contacts excluded), which prevents a wrong assumption about the archive's contents.

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?

Two dense sentences with no filler: the output artifact and its constraints first, then the cost and exclusion caveat. The opening fragment lacks a leading verb, so it reads as a continuation of the title rather than a self-contained statement, but nothing is redundant.

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?

There is no output schema, so the description carries the return-value burden and does so well by describing the link's lifetime, format, and contents. Missing only minor details such as whether generation is synchronous or job-based, and how a quota-exhaustion failure manifests.

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 a single parameter at 100% schema description coverage, the schema already explains that folder_id comes from list_folders or get_folder. The description adds nothing about the identifier itself, but it does usefully reinforce the recursive scope of that folder (the folder 'and everything under it'), which is a semantic fact the schema does not encode. Baseline 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 concretely says what the call produces: a one-use, 15-minute download link for a zip containing the folder and everything beneath it, one CSV per record kind. That level of specificity separates it cleanly from siblings like get_folder or list_folders, though the sentence is a noun phrase and never states the action verb directly (the name and title carry that).

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?

Usage context is only implied: the mention that downloading consumes the account's monthly export rows signals this is a metered, non-casual operation, which steers an agent away from routine calls. However, there is no explicit when-to-use/when-not guidance and no named alternative (e.g., search-based retrieval or get_search_matches) for agents who only need a subset.

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