Scene Open

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

No annotations are provided, so the description carries the full burden. It discloses important behaviors: the no-op case, force_reload behavior (discarding in-memory edits), the reply timing (only after editor switches, with switched flag), and the settle states ('timeout', 'not_waited'). It also handles synchronous contexts. This is rich behavioral detail beyond what any annotation might provide. Slight deduction because it doesn't explicitly mention permissions or side effects (e.g., does opening purge unsaved changes in other scenes?), but it's quite transparent.

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 moderately sized but packs a lot of necessary information. It's structured with paragraphs and list-like formatting (with backticks for parameters and field names). It front-loads the core purpose and then explains edge cases. While it could be slightly more concise (some might argue the synchronous context paragraph is dense), it's well-organized and every sentence carries meaning. Not a 5 because it lacks a summary or roadmap, but it's good.

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 that the tool has an output schema (though not shown in the prompt, it's indicated as present), the description doesn't need to explain return values. It covers all aspects needed for an agent to use it correctly: what it does, when to use force_reload, what the settle flags mean, how to handle synchronous contexts, and how to verify success. The complexity is moderate (3 params, one required), and this description is complete for the task. It even warns about follow-up writes, which is important for sequencing.

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 100%, so the schema already documents all parameters with descriptions. The description adds significant value by explaining the semantics of force_reload in context (discarding edits, file authority) and the meaning of the switched and settle fields. It also clarifies the no-op condition dependent on path. This goes beyond the schema's basic parameter descriptions, earning a 4.

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 tool clearly states its purpose: 'Open an existing scene file (.tscn) in the editor.' It uses a specific verb, resource, and file type. While sibling tools like scene_save, scene_manage, and scene_get_hierarchy are related, the description hints at its distinct role (opening) but doesn't explicitly differentiate from siblings like scene_manage (which might also involve opening). It's clear enough but doesn't name alternatives, so it doesn't quite reach a 5.

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 provides excellent usage guidance. It explains when force_reload is appropriate ('when the file on disk is the authority'), warns about synchronous contexts (batch_execute) returning immediately, and advises re-checking editor_state before follow-up writes when switched is false. It even notes that if path is already the current scene, it's a no-op preserving in-memory state. This gives clear when-to-use and cautionary guidance, though it doesn't explicitly name alternative tools for opening vs managing. Still, it covers usage conditions thoroughly.

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