capture_downloads

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

Goes well beyond the annotations: it discloses the interception trick (downloads cancelled at once, bytes re-fetched with browser cookies), filename sanitization, the never-overwrite guarantee, and the max_mb cap with skip behavior. Annotations only cover the generic safety profile (readOnly=false, idempotent=false, destructive=false), so this richer detail is real added value, and it is consistent with them.

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?

Front-loads the key distinction (no browser download, no Save-as dialog) and packs the workflow into one dense paragraph where almost every clause carries information. It is somewhat run-on across three distinct ideas, but there is little dead weight.

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 stateful three-action tool with no output schema, the description covers the lifecycle, side effects, return value ('returns the saved paths'), and the cross-tool escape hatch. Nothing an agent needs to invoke it correctly is missing.

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 coverage is 100%, so the per-parameter semantics are already documented; the description's contribution is tying parameters to the stateful workflow ('arm with save_dir', cap via max_mb, wait returns paths). This adds a little context on how params combine across the arm/wait/disarm cycle, but largely reinforces what the schema says.

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?

Names a specific verb+resource ('Save files the page builds itself') and enumerates exactly the mechanisms covered: blob/data URL a[download], showSaveFilePicker writes, and page-initiated downloads. This cleanly separates it from siblings like save_page, manage_downloads, and http_request, which the description explicitly routes away.

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?

Gives an explicit operational sequence ('arm with save_dir, then click Export/Download, then wait') and names the alternative for the out-of-scope case ('A file with a URL: http_request save_to instead'). Both when-to-use and when-not-to-use are stated.

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