manage_linked_data

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

No annotations exist, so the description carries the full burden and does disclose key traits: linked data is read-only in this file, MAKE_LOCAL is destructive to the link, OVERRIDE preserves the link with selective editability, and library is required for RELOAD. It does not say what happens to local edits on RELOAD or to overrides on MAKE_LOCAL, nor whether these operations are undoable.

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?

Front-loaded summary, then a short conceptual paragraph, then Args/Returns — easy to scan and no filler in the action descriptions. The Returns section is largely wasted since an output schema already exists, and the opening parenthetical is doing less work than the body.

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 4-param, four-action library-management tool with no annotations, the description covers the conceptual model (linked vs local vs overridden) that an agent cannot infer from the schema. Remaining gaps are edge behavior: effect of RELOAD on local changes and on existing overrides, and error conditions when a library or data-block name is missing.

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 does: action gets per-value semantics, data_type is enumerated (OBJECT, COLLECTION, MATERIAL, NODE_GROUP, WORLD, MESH) beyond the schema's untyped string, data_name is scoped to MAKE_LOCAL/OVERRIDE, and library's dual role (required for RELOAD, disambiguator for duplicate names) is spelled out.

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?

Opens with a specific verb+resource ('Work with data linked from other .blend files') and immediately names the two adjacent operations (link_or_append, place_asset) so the agent can place it against the linking siblings. The enumerated action set (LIST/MAKE_LOCAL/OVERRIDE/RELOAD) narrows the scope further than the tool name alone would.

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?

Each action is given a situational gloss: LIST enumerates state, MAKE_LOCAL copies and cuts the link, OVERRIDE keeps the link editable with library updates flowing through for unchanged data, RELOAD re-reads from disk. That is genuine when-to-use guidance for a multi-action tool. It stops short of explicit 'do not use this when...' routing back to link_or_append/place_asset, which are only mentioned in passing.

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