gpu_trace

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

With no annotations, the description carries the full burden of disclosing behavioral traits, but it only says 'collect... from the device.' It does not mention whether the tool modifies device state, requires specific permissions, or affects ongoing processes, leaving significant behavioral gaps.

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 concise sentence with no unnecessary words, but it is too brief to be useful. Front-loading is present, but the brevity sacrifices substance for conciseness.

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 5 parameters, no schema descriptions, and the presence of an output schema (not shown), the description is woefully incomplete. It fails to explain what the tool outputs, any dependencies (e.g., device connected), or how the parameters interrelate, leaving the agent underinformed.

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?

The schema has 0% description coverage, meaning none of the 5 parameters have explanations. The description adds no detail about what 'target', 'local_filename', 'login', 'http_port', or 'name_type' mean, leaving the agent to guess their purpose and format.

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 clearly states the tool collects a gpu-trace zip from the device, which is a specific resource and action. However, it does not differentiate this tool from sibling tools like 'rgp_capture' or 'screenshot' that also capture performance data, leaving the agent uncertain about when to use this tool specifically.

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 guidance is provided on when to use this tool versus alternatives or when not to use it. The description lacks any context about prerequisites, scenarios, or exclusions, forcing the agent to infer usage 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.