gb_gpu_snapshot

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description discloses that this is an alias pointing to another tool, which is transparent about the indirection, but it reveals nothing about the actual behavior: whether this reads or mutates emulator state, whether it writes files to output_dir, what a snapshot entails, or any side effects. For an unannotated tool with real parameters like output_dir, this is a meaningful gap.

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?

The description is a single, tight sentence that states the alias relationship and the canonical target with the fixed target='gb' parameter. It is front-loaded and efficient with zero waste. It could arguably be slightly more informative, but for an alias description it is appropriately concise.

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?

Given no output schema and no annotations, and given that the actual behavior of the underlying GPU snapshot tool is never described, the completeness is weak. The description tells the agent what this tool IS (an alias) but not what the GPU snapshot operation does, when to use it, or what its return/value is. The alias pointer partially compensates by routing the agent to emulator_gb_gpu_snapshot, but the description alone leaves an agent relying on the canonical tool's own documentation.

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 there are 3 parameters (render, output_dir, include_raw). The description adds zero parameter-specific information beyond the schema. However, since the description explicitly declares this is a pure alias for emulator_gb_gpu_snapshot with target='gb' fixed, the parameter semantics are effectively inherited from the referenced tool. Given the alias framing, the agent can reasonably look up the canonical tool's schema; a baseline 3 is appropriate but no extra semantic value is added here.

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 description identifies this as a 'Legacy-short alias' for emulator_gb_gpu_snapshot(target='gb'), which communicates it's a redirect but does not state what the underlying tool actually does or what a GPU snapshot is. The purpose is implied through the alias relationship and the tool name, but the agent must infer the actual function. It does distinguish from siblings by naming the canonical target, but the actual behavior is opaque.

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 description clearly directs that emulator_gb_gpu_snapshot(target='gb') is the canonical equivalent, which implicitly tells the agent this is a redirect to that tool. However, it offers no when-to-use or when-not-to-use guidance, and does not explain why an agent would pick this alias versus calling the canonical tool, versus any of the other emulator_* sibling tools. The use context is entirely dependent on the agent already knowing what GPU snapshots are for.

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