get_last_scene_diff

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

With no annotations provided, the description carries the full burden. It discloses that the tool fetches from a cached pair and pretty-prints the diff, implying a read-only operation. However, it does not reveal edge cases such as behavior when no cached diff exists or potential errors, leaving some behavioral ambiguity.

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 concise sentences, with the primary action front-loaded. The second sentence adds valuable context about the server-side caching and the purpose for the agent. Every sentence earns its place, and there is no redundant wording.

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?

For a zero-parameter tool with an output schema, the description adequately explains what the tool does and why it exists. It references related concepts (execute_code, serialize_scene_state) that are part of the sibling tool ecosystem. However, it could be slightly more complete by mentioning prerequisite conditions or error scenarios, but overall it is sufficient.

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 tool has zero parameters, so the baseline is 4. The description correctly avoids adding parameter details that don't exist, and the schema coverage is trivially 100%. No additional semantic info is needed.

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 uses a specific verb ('Return') and identifies a precise resource (the last execute_code scene diff). It clearly distinguishes itself from sibling tools by referencing the capture_diff=True mechanism and the caching of serialize_scene_state pairs, making the tool's unique function unambiguous.

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 states the intended use case: to verify what a privileged execution changed in the scene. This provides clear context for when to use the tool. However, it does not explicitly mention when not to use it or suggest alternatives, though the specialized nature makes the context sufficient.

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