loader_manage

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

No annotations are provided, so the description carries the full burden—and it delivers: it discloses asynchronous/threaded/background execution, the canonical call shape ('Canonical call shape: {"op": ..., "params": ...}'), the flat-alias compatibility behavior, and status/progress ranges (0.0-1.0, in_progress/loaded/failed). The only gaps are error-handling behavior on failure and side effects, but the described invocation contract is substantial.

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?

Well-structured: a one-line purpose summary front-loads intent, then a tight bulleted op list earns its space because the schema is opaque and needs the per-op parameter documentation. The canonical-call-shape line adds genuine invocation value. Slightly verbose for four ops, but every sentence pulls its weight given the opaque schema.

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 multi-op tool with an opaque params schema, zero annotations, and an output schema that the agent must interpret, this description is nearly complete: it covers all ops, their parameters/defaults, the call envelope, and status result values. Minor omissions—failure semantics and routing vs. sibling tools—keep it from a 5, but it's strong given the tool's complexity.

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% and the schema's params field is a generic anyOf object with additionalProperties true, so it documents nothing. The description fully compensates by documenting every op's parameters with names, types, defaults (e.g., start_load(path, type_hint="", use_sub_threads=false, cache_mode=1)) and per-op signatures. This is where the description adds the most value, beyond what any structured field provides.

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?

The very first line names a specific purpose: 'Asynchronous Threaded Resource Loading, Progress Polling, and Loading Screen Scaffolding.' The four ops are each given a verb + resource + documented parameters (start_load, get_status, get_resource, scaffold_loading_screen), leaving no ambiguity about what the tool does or how it separates from the broader *_manage family.

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 op list makes the tool's jobs clear (async load, poll progress, retrieve results, scaffold a loading screen), so usage is implied well. However, with ~90 siblings including resource_manage, scene_manage, and filesystem_manage, the description never states when this tool is preferred over alternatives or when NOT to use it (e.g., sync loading, direct resource access). The guidance is implied, not explicit.

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