Profile capture replay

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

With no safety annotations (all hints false), the description carries the burden of disclosure. It transparently reveals that the tool executes GPU work in a hidden, vsync-off window and is not a static read, which is critical behavioral context. It does not describe all side effects (e.g., file creation in output_directory), but the disclosed behaviors are valuable and accurate.

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 two sentences, front-loaded with the main action and output, followed by a crucial behavioral warning. Every word contributes value, with no redundancy or filler. It is an exemplary concise yet informative structure.

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?

The description gives a solid overview of the tool's purpose and execution, but with no output schema, it does not explain the return format or how the summary is delivered (e.g., stdout, file). The mention of output_directory in the schema implies file artifacts, but the description doesn't elaborate. For a moderately complex tool with six parameters, more detail on outputs and workflow would be needed for full completeness.

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 67%, leaving loop_count and timeout_seconds without descriptions. The tool description does not compensate for these gaps; it only mentions 'optional GPU frame-time' which maps to collect_gpu_time, adding no new meaning beyond the schema. Thus, the agent may not understand the semantics of two parameters, making this dimension weak.

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's function with specific verb ('Replay' and 'summarize') and resource ('capture'), and lists precise measurements (CPU submit, finish-wait, reset, FPS, screenshot-difference, optional GPU frame-time). This distinguishes it from sibling tools like inspect_capture or analyze_capture by focusing on replay-based profiling.

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 provides clear context about when this tool is appropriate: when you need per-iteration profiling measurements from a captured replay. It also gives an implicit exclusion by stating 'This executes GPU work; it is not a static read,' signaling that it is not for passive inspection. However, it does not name alternative tools explicitly, so it falls short of a 5.

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