rename_scene

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

Annotations already carry the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), so the bar is lower. The description adds a useful state-dependent trait — the tool only works after another scene is loaded — but the self-contradictory phrasing muddles which scene is actually renamed, so the behavioral truth is not clearly disclosed. No contradiction with annotations: renaming is a non-destructive, idempotent mutation.

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?

Two short sentences, front-loaded with the core action and no filler. It loses a point because a slightly longer, more explicit phrasing could have resolved the contradiction between 'currently loaded scene' and 'load another scene first'.

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 simple single-parameter mutation with no output schema and adequate annotations, the description covers the action and a precondition — close to sufficient. But the internal inconsistency plus total silence on naming constraints means an agent may need to attempt the call to discover the actual contract.

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 compensate, yet it never addresses the 'name' parameter directly. An agent can infer that name is the new scene name from the tool name alone, but there is no guidance on format, uniqueness, disallowed characters, or whether an extension is appended — leaving a single required parameter underspecified.

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 specifies a clear verb (rename) and resource (a scene), and the phrase 'currently loaded scene' differentiates it from siblings like create_scene, duplicate_scene, delete_scene, and load_scene. However, the second sentence ('Load another scene first to rename it') introduces ambiguity about which scene is actually being renamed, suggesting the current one must first be unloaded — the two sentences sit in tension.

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?

It provides an actionable precondition ('Load another scene first to rename it'), which tells an agent when the call is valid. But it never names alternatives or explains when to prefer this tool over scene-related siblings, and the precondition's relationship to the 'currently loaded scene' claim is left unclear.

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