reels_download_asset

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

The annotations already declare readOnlyHint=false and openWorldHint=true, and the description adds genuinely useful context beyond them: downloads traverse the network, checksums are verified, outputs are consolidated into a single GLB, and the asset is written into a shared bank. It also discloses caching (reuses existing downloads) and a workflow gate (visual review for new candidates). Gaps remain around what happens on checksum failure, whether an existing bank entry is overwritten, and what the tool returns, which is why this is not a 5.

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 sentences, front-loaded with the main action, with no filler. The trailing 'Powered by Poly Haven' is marketing rather than operational information and could be cut, and 'register in the shared bank' would be clearer if it named the concept directly.

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 network-facing mutation tool with no output schema, the description covers the pipeline stages but omits what an agent needs to act on afterward: the returned identifier or path, failure/retry semantics for checksum mismatches, and how the 'visual review' gate is satisfied via a sibling. Adequate but not complete.

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 carries the full burden for two parameters and does not mention either by name. 'providerId' is never explained beyond the vague 'a selected Poly Haven model', and the resolution enum (1k/2k/4k) is only obliquely gestured at by 'PBR textures' with no indication of the default or its cost/quality tradeoff.

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 concrete verb and resource chain: download a Poly Haven model plus PBR textures, verify checksums, embed into one GLB, and register in the shared bank. That is clearly distinct from lightweight siblings such as reels_get_asset or reels_preview_asset. It stops short of 5 because the phrase 'a selected model' never says how the providerId points at that selection, and 'register in the shared bank' is jargon that is not tied to reels_register_asset.

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 sentences 'Reuses existing downloads' and 'New candidates require visual review' imply when this tool is appropriate: after a candidate has been reviewed and when the asset is not already fetched. However, no sibling is named as an alternative, and there is no explicit when-not guidance (e.g., use reels_import_asset for non-Poly Haven sources, or reels_preview_asset before committing). Usage is inferable but not routed.

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