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

Goes well beyond the annotations: ttl default and range, 2 GB size ceiling, 'only works while the sandbox runs and only for that path', 'treat it as a secret', and that the link dies with the sandbox. The annotations only give generic hints (readOnlyHint false, openWorldHint false), so this behavioral detail is genuinely additive.

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?

Tightly front-loaded: what the link is, its lifetime, then the curl usage and constraints. Minor redundancy — 'only works while the sandbox runs' is restated at the end as 'dies with the sandbox' — keeps it just short of a 5.

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?

No output schema, so the description must explain the returned value, and it does: a short-lived secret URL that streams one file. Lifetime, size limit, usage recipe, and the token/sandbox precondition are all covered, leaving nothing an agent needs in order to call it correctly.

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 100%, so ttl range/default and the absolute-path requirement are already documented in the schema; the description repeats the ttl default and range without adding syntax. The only extra semantic is the 2 GB max file size, which is not expressible in the schema. 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?

States a specific verb ('Get'), a precise artifact ('short-lived HTTPS link') and a bounded resource ('streams ONE file from the sandbox — e.g. a build artifact or archive'). The phrase 'without base64 in this conversation' implicitly distinguishes it from the sibling download_file, so an agent can route correctly without opening the schema.

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 clear operating context — call it when you want a link you can pull with `curl -fL -o <name> <url>` from wherever you work, requiring token + live sandbox_id. It implies the alternative (inline base64 download) but never names download_file or get_upload_url, so the when-not-to-use side is only inferred.

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