ai_export

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the safety profile is already covered; the description adds that preview:true returns the PNG inline, which is useful behavioral context. It does not say where non-inline exports are written, whether existing files are overwritten, or what is returned for non-PNG formats — gaps that matter for a file-producing tool. No contradiction with annotations.

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?

One dense sentence, app-scoped up front, format details grouped in a single parenthetical, and the preview return behavior last. Nothing is redundant and every clause carries information.

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 must frame the return value — it only covers the PNG-inline case and says nothing about the result of file-based exports. With 7 optional parameters and an undocumented 'path', an agent still lacks the destination-file story needed to call this confidently.

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 coverage is only 14% (just the 'document' description), so the description carries most of the burden — and it does explain format choices (png/jpg/svg/pdf/psd), the 'scale %' semantics, 'transparent', and the preview return behavior. Notable omissions are 'path' (the destination is never explained) and 'artboard' being an integer index despite the plural 'artboard(s)' phrasing.

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?

Uses a specific verb (export) plus resource (artboard(s) or the document) and enumerates every supported output format, all scoped to Illustrator by the leading app prefix. An agent can distinguish this from ps_exportLayers, ae_exportFrame, or pr_export without opening any schema.

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 parenthetical 'psd (layered, for Photoshop/AE)' hints at a downstream-handoff use case, and 'artboard(s) or the document' implies a scoping choice, but the description never states when to pick this over sibling export/preview tools (ps_preview, xapp_preview, ae_exportFrame). Usage is implied rather than prescribed.

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