rastermoves_download_refiner

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

Goes beyond the annotations by naming the concrete effect flags (write, download, network) an agent must acknowledge, disclosing that the call spawns a retained background job rather than returning a result, and flagging that inference/download effects are conditional and must be inspected. The destructiveHint=true annotation is not directly explained, but the disclosure of write/download effects is consistent with it rather than contradicting it.

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?

Four short, front-loaded sentences with no filler; the core action leads and the operational follow-ups trail. The 'Base effect flags' line is telegraphic in a way that is dense but still parseable for an agent.

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?

The tool returns a job handle, and an output schema plus the explicit 'poll danceflow_job_status' instruction make the return path clear. Given annotations already convey the safety profile, the main remaining gap is guidance on when this prefetch is preferable to rastermoves_download.

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 50%; only allow_downloads is documented in-schema. The word 'Explicitly' and the pinned-refiner phrasing hint at consent for downloads and at immutable pinned revisions, but cache_dir and strict_checksums receive no meaning from the description, and the two enum refiner values (sd15-tile, sdxl-tile) are never explained.

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 and resource: 'Explicitly prefetch one canonical pinned refiner,' which tells an agent this is a single-refiner prefetch rather than a general model download. It does not explicitly distinguish itself from the sibling rastermoves_download or rastermoves_sync, so the boundary is inferable rather than stated.

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 useful downstream guidance ('poll danceflow_job_status') and a diagnostic path ('Inspect danceflow_component for conditional inference/download effects'), which covers the after-call flow. However, it never says when to choose this over rastermoves_download or rastermoves_refiners, so selection between sibling tools is left to inference.

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