pixabay_download

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

Annotations only declare write/open-world/non-destructive; the description adds substantive behavior beyond that: files are written to disk, and the achievable size depends on the caller's API key tier ('best size your key allows ... full-res / vector SVG/AI with full API access'). That key-gating detail is exactly the kind of non-obvious constraint annotations cannot express. It omits what happens on size-denial or invalid IDs, keeping it below 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?

A single dense sentence that front-loads purpose and failure-relevant detail (ID source, size gating) before the optional import. The nested em-dash/parenthetical clauses make it slightly harder to parse than a short multi-sentence version would be, but nothing is wasted.

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?

There is no output schema, so the description should tell the agent where files land and what the call returns, but it never mentions the 'outputDir' parameter or default download location, and it is silent on behavior when a requested size exceeds the key tier or an ID is invalid. The import half of the tool is described only by app names, not by what import actually requires or does.

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 carry the load. It does explain the most consequential parameter well — 'size' semantics differ by type (images: large 1280px / full-res / vector; videos: large 4K/1080p, medium, small, tiny) — and clarifies that ids come from search. But 'outputDir' is never mentioned and the nested 'importTo' object (bin, time, track, sequence, addToComp, compositionName) is reduced to a bare list of four apps, leaving 7 sub-fields undocumented.

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 ('Download Pixabay assets by id ... to disk') plus the second action ('optionally import them into AE / Premiere / Photoshop / Illustrator'). It also names its upstream sibling pixabay_search as the ID source, so an agent can distinguish it from the search tool immediately.

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?

Explicitly positions the tool downstream of pixabay_search ('by id (from pixabay_search)') and explains that import into host apps is optional, giving clear sequencing context. It stops short of stating exclusions (e.g. when to prefer media_import or that IDs must be valid search results), so it is strong but not exhaustive.

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