fusion_run

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

Annotations declare destructiveHint=true and openWorldHint=false, but the description adds genuinely non-derivable behavior: the 90 s timeout, execution on the main thread, the whitelist of blocked operations (file deletion, network, cloud save), and that a rollback checkpoint is returned. It doesn't state what happens when the timeout fires or how errors surface, which keeps it from a 5.

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?

Three tight sentences with the constraint-heavy information (main thread, 90 s limit, blocked operations) front-loaded. It is dense with useful signal rather than padded, though the unexplained abbreviations (P3, VI, FO, IN) cost some readability.

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?

With no output schema, the description correctly explains the return contract (set `result`, receive a checkpoint for fusion_rollback), and it covers the sandbox behavior an agent needs before executing arbitrary code. The main residual gap is `label` and error/timeout semantics.

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 coverage is 0%, so the description must carry the load. It does well for `code`, documenting the predefined symbols (app, ui, design, adsk, P3, VI, FO, IN, coll, board) and the `result` output convention, but `label` is never mentioned, leaving one of two parameters completely undefined.

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?

States a specific verb and resource ('Run Python inside Fusion's main thread') and adds the 90 s execution limit, which immediately scopes expectations. It partially differentiates from siblings by naming fusion_rollback as the consumer of its output, but doesn't distinguish itself from fusion_api or fusion_ui_command, which are the closest alternatives.

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?

Usage is implied rather than prescribed: the agent can infer this is the escape hatch for arbitrary scripting, and the description links it forward to fusion_rollback. However, it never says when to prefer this over fusion_api or fusion_ui_command, nor what prerequisites (document open, add-in state) must hold.

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