adobe_pluginFile

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

Annotations already declare non-read-only, non-destructive, closed-world behavior, and the description adds real value on top: write creates a .mcpbak backup before mutating and restore recovers from it, plus an explicit folder-scope restriction. Minor omission is whether write creates new files or overwrites existing ones, and whether the backup replaces prior backups.

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?

Three tight sentences: purpose with examples first, then the action semantics, then the scope restriction. No filler and no repetition of schema fields.

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 mutating, zero-output-schema tool it covers the essentials (backup behavior, scope), but leaves unclear what list/read return, whether write can create new files, and how the folder restriction is enforced when violated.

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 compensate, and it does explain all four action enum values and their effects. But the content parameter — required for write to be meaningful — is never mentioned, and path is only obliquely defined via the folder restriction.

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 pair (read/edit) and a specific resource (files of an installed extension/script/preset) with concrete file-type examples (manifest.xml, panel HTML/JS, host .jsx, UXP manifest.json). It is clearly not a generic file tool, though it never explicitly distinguishes itself from nearby siblings such as adobe_extensions or adobe_runScript.

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 action list (list/read/write/restore) implies usage and the closing restriction to Adobe plugin/extension/script folders bounds the context. However there is no explicit when-to-use or when-not guidance, and nothing tells the agent why to pick this over adobe_runScript or adobe_extensions.

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