prepare_download

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

The readOnlyHint annotation already tells the agent this is a safe, non-mutating operation, so the description gets credit mainly for the two traits it adds: the URL is "short-lived" and the ZIP ticket is "restricted". However, neither is quantified — no expiry window, no explanation of what the restriction enforces or whether the ticket is tied to the caller — and nothing says whether repeated calls are needed per file.

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?

A single well-formed sentence with the primary outcome ("short-lived direct GET URL") front-loaded and the alternate mode following immediately. There is no filler, hedging, or redundant restatement of the tool name.

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?

An output schema exists, so return-value explanation is not required, and the readOnlyHint covers safety. What remains unaddressed is meaningful for a tool with zero required parameters: whether an empty call is valid, which of paths/node_id/node_ids wins if several are passed, and how long the URL or ticket lasts before the caller must re-invoke.

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 the field-level docs already explain that "paths" replaces node IDs, that "node_id" is a single UUID, and that "node_ids" is for batches. The description reinforces the one-file versus multiple-node distinction but adds no format, precedence, or mutual-exclusivity rules beyond what the schema states, so the baseline of 3 applies.

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 gives a specific verb ("Create") and two concrete resources — a "short-lived direct GET URL" for one file versus a "restricted ZIP ticket" for folders and multiple nodes — so an agent knows exactly what the tool produces. It distinguishes the single-file and batch modes internally, but never names a sibling (e.g. prepare_upload or read_text_file) that it should be preferred over, which keeps it short of a 5.

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 is only implied: the two modes hint that a single file gets a direct URL while folders/multiple nodes get a ZIP ticket, letting the agent infer which inputs map to which behavior. There is no explicit when-to-use or when-not-to-use guidance, no mention of an alternative tool for streaming or text extraction, and no statement about what happens if no path or node is supplied.

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