Unembed a placed file in Adobe InDesign and save it as a linked resource, replacing an embedded copy with an external link.
Unembed a file and save as linked resource
| Name | Required | Description | Default |
|---|---|---|---|
| filePath | Yes | ||
| linkIndex | Yes | ||
| document_id | No | Which open document to act on: a name (see document_listOpen) or a 0-based index. Defaults to the front document. |
Changes observed during successful MCP inspections.
v1.6.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and falls short. It does not say what happens to the embedded file data, whether an external file must exist at the path, whether the operation is reversible, or whether the document must be saved afterward — all critical for a mutation that changes how assets are stored.
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 short sentence with no filler, but its brevity comes from under-specification rather than tight writing. It is appropriately front-loaded but earns little beyond the title-level statement.
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 an unannotated mutation touching document resources, with no output schema and two of three parameters undocumented, the description omits prerequisites, side effects, and parameter meaning. An agent could invoke it but cannot predict the result or the failure conditions.
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 only 33%: only document_id is documented, while filePath and linkIndex (both required) have bare type definitions. The description adds nothing about either — e.g. what linkIndex indexes into or whether filePath must point to an existing file — so the coverage gap is not compensated.
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?
Names a specific verb ('Unembed') and a specific resource ('link'/'linked resource'), which is enough to distinguish it from the opposite-direction sibling resources_embedLink. It does not, however, reference any sibling by name or clarify how it differs from resources_updateLink or resources_getLinkInfo.
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?
No when-to-use guidance at all: it never says when an agent should unembed rather than embed, update, or list a link, nor what preconditions apply (e.g. the link must currently be embedded). The agent must infer the use case from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.