ai_placeFile

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

Annotations already declare non-destructive, non-readOnly, closed-world, so the safety profile is covered. The description adds real value by disclosing that trace alters the result ('expands to vectors') and that embed toggles linked-vs-embedded storage, but it never says whether the operation is reversible, whether an existing link can break, or that Image Trace can be slow on large files.

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 with the app name front-loaded and no filler; every clause carries a distinct parameter or behavior. It is slightly run-on – the semicolon-chained clauses strain readability – 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?

With no output schema, the description should say what the agent gets back (a placed-item reference? the traced group?) and does not. For a 9-parameter mutation into a live document, the unresolved name/layer semantics and the absence of any return-value statement leave meaningful gaps.

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 11%, so the description must carry weight, and it does for the most consequential parameters: position as [x,y], width keeping aspect ratio, embed, trace, and even concrete tracePreset examples that the schema lacks enums for. However, name, layer, and path are left completely undefined, so three of nine parameters remain unexplained in both places.

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?

'Illustrator: place an image/PDF/PSD/SVG file' names a specific verb, resource, and host app, which disambiguates it from ps_placeFile and the many ae_import/place siblings. An agent knows exactly what object this creates without opening the 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 embed/link and trace/no-trace branches are implied by the phrasing ('embed:true embeds it', 'trace:true runs Image Trace'), giving some selection guidance. But there is no explicit when-to-use vs when-not, and the important ambiguity against ai_openFile (place into the current document vs open as a new document) goes unaddressed.

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