fetch_scene

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

The description states that 'Everything done since is discarded,' which is a destructive behavior. This directly contradicts the annotations readOnlyHint=true and destructiveHint=false, which imply the tool is a safe, non-modifying operation. The contradiction is flagrant and could mislead an agent into believing the tool has no side effects when it actually discards user work.

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 extremely concise: two short sentences in each language, with the key warning bolded and front-loaded. No extraneous information is present, and the structure makes the critical destructive consequence immediately visible.

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 tool with no parameters and no output schema, the description covers the core behavior and main warning. However, it omits important context such as what happens if hold_scene has never been called, whether the undo stack is affected, and how this relates to release_scene. The contradictory annotations also reduce trust and completeness, as an agent cannot confidently determine the tool's true safety profile.

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, and the input schema is an empty object with 100% coverage. Per the baseline for 0-parameter tools, a score of 4 is appropriate. The description does not need to explain parameters since there are none, and it correctly focuses on the behavior.

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 restores the scene to the last hold_scene state, using a specific verb ('restore') and resource ('scene'). It distinguishes itself from siblings by directly naming hold_scene as its counterpart and explicitly warning that all changes since are discarded, leaving no ambiguity about its function.

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 implies the usage context: call this after a hold_scene to revert to that state. It clearly communicates the effect of discarding subsequent changes. However, it does not explicitly mention alternatives like undo_last or release_scene, nor does it state when not to use it, so it stops short of full exclusion guidance.

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