download_query

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

With no annotations provided, the description carries the full behavioral burden and discharges it thoroughly. It discloses that the tool returns immediately with a job_id, runs independently of the conversation, writes to a fixed server-configured root the user cannot override, restarts interrupted downloads from scratch with no resume support, and hides file sizes until a transfer begins. These are exactly the operational surprises an agent needs to know before calling.

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 long (~250 words) but front-loaded with the core purpose and heavily information-dense; nearly every sentence adds operational value, including the async watcher pattern and the large_download handoff. A few parentheticals ('the portal reveals them only then') are slightly redundant, so it is not perfectly tight, but the length is largely justified by the tool's complexity.

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 and no annotations, this description is remarkably complete for a complex async tool. It covers prerequisites, parameter semantics, return value (job_id), the asynchronous lifecycle, failure behavior, exclusions, and alternatives — including the non-obvious advice to delegate a background watcher via download_wait. Nothing an agent needs to invoke and supervise this tool correctly is left unspecified.

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 0%, so the description must fully compensate, and it does. slug is grounded ('Give the slug from save_query or list_queries'), force is explained ('re-downloads files already present'), and select gets richer semantics than the bare schema: '1-based indices or full scene IDs; omit it for the whole query.' Every parameter is given meaning the schema alone cannot convey.

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 opening sentence, 'Download a saved query's open-access scenes in the background,' states a specific verb (download), a precise resource (a saved query's open-access scenes), and the execution mode (background). It differentiates clearly from siblings: preview_download (previews rather than downloads), download_status/download_wait (monitor rather than initiate), and search_scenes (searches rather than downloads).

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 is explicit about when to use this tool: it tells the agent where to get the slug ('from save_query or list_queries'), names a prerequisite ('Needs a login (see auth_status)'), and gives specific exclusions with alternatives ('Priced and on-order scenes are skipped — stage those with cart_add instead'). It also instructs how NOT to use it (never block by sleeping and re-polling) and directs to the watcher/download_wait pattern and large_download for oversized transfers.

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