dump_images

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

The description discloses the main behavior: the tool replays the trace and writes PNG files, and it can do so per frame or per call. This goes beyond the annotations, which are all false and uninformative. However, it does not mention side effects like file naming, overwrite behavior, or whether a full trace replay could be expensive or long-running, leaving gaps in the behavioral picture.

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 compact, with the core functionality front-loaded in the first sentence and the use case in the second. It avoids redundancy and stays focused, though the second sentence is slightly casual with phrases like 'and look'.

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 the tool's complexity—five parameters, one required, full trace replay, and file output—the description is not complete enough. It omits critical input semantics such as what mrt controls, what out_prefix does, and how calls is expressed. The presence of an output schema reduces the need to describe return values, but it does not fix the missing input guidance.

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. It adds meaning for the calls parameter via 'per frame, or per specified call' and for the output format via 'PNG images', but it leaves trace, mrt, timeout, and out_prefix entirely unexplained. This is insufficient for a five-parameter tool with no schema-level descriptions.

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 states a specific action and resource: 'Replay the trace and write PNG images'. It also specifies granularity ('per frame, or per specified call'), which makes the tool's purpose clear. However, it does not explicitly compare against sibling tools such as diff_images or dump_calls, so it falls short of full differentiation.

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 gives a practical use case: 'finding *which* draw call produces the HUD, the world, or the problem'. This implies when the tool is useful, but it does not say when to prefer it over alternatives, nor when not to use it. There are many sibling tools, and the description provides no routing guidance.

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