dump_state

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

The description goes well beyond the readOnly/idempotent annotations by disclosing that replay executes on the local GPU, is slow, can fail on old games, and outputs JSON. It also clarifies an upstream limitation for DirectDraw/D3D7. These are non-obvious behavioral traits that an agent needs to anticipate.

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 main action is front-loaded in the first sentence, followed by a useful analogy and then caveats. The description is a bit longer than strictly necessary, but every paragraph contributes functional information. It is well structured and readable.

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 covers output format, execution cost, failure modes, and a fallback strategy, while annotations cover safety and idempotence. Since an output schema exists, return-value details are not needed. The only meaningful gap is the semantics of the optional api and timeout parameters, which keeps it from being fully complete.

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 carry parameter meaning. The description implies the roles of 'call' and 'trace' via 'up to a call' and 'run the trace', but it does not explain 'api' or 'timeout'. An agent can infer the required parameters from names, but optional parameters remain undocumented.

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 ('Replay up to a call') and a precise result ('dump the full pipeline/device state as JSON'). This clearly distinguishes dump_state from siblings like dump_images, dump_calls, and diff_state. The RenderDoc analogy reinforces intent without obscuring it.

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 concrete when-not-to-use guidance: DirectDraw and D3D7 traces cannot be replayed for state inspection. It also recommends trim_trace as a fallback when replay fails. It does not explicitly compare against diff_state or other alternatives, but the context is sufficient for an agent to decide when this tool applies.

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