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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, but the description goes further: it says the tool 'queues no job, spends no compute and changes nothing' and is 'always safe to retry, including after a transport-level error'. It also explains that schemas are introspected from the validator itself, so results exactly match what scene_apply accepts. This is rich behavioral context beyond the annotations and does not contradict them.

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 long but every sentence earns its place: the primary use is front-loaded, alternatives and exclusions are stated early, and each optional parameter's behavior is covered efficiently. The 'READ ONLY and free' safety note is a deliberate closing signal. No filler or redundant restatement of schema fields.

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?

The tool has six optional parameters, an output schema, and several sibling tools, but the description covers all necessary invocation patterns, special values, result formats, and the caveat about repeated-detail namespaces. It also explains the tool's cost/safety profile, which matters for an agent deciding whether to retry. An agent has everything needed to select and call this tool correctly.

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 baseline is 3, but the description adds meaning the schema lacks: it explains op='guide' compatibility with older catalogs, what namespace='mesh' does, the caveat that repeated details live under object.radial_array rather than a 'pattern' namespace, and that search returns ranked matches. It also clarifies the format parameter's relationship to structuredContent, which adds real value for an agent choosing how to consume results.

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: 'Enumerate and inspect the validated operations scene_apply accepts'. It also distinguishes the tool from siblings by saying 'call this BEFORE reaching for scene_script' and noting most modeling does not need raw bpy, which separates it from the docs_bpy tools. No ambiguity about what the tool is for.

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?

Explicitly names when to use the tool (before scene_script), when not to use raw bpy, and which sibling handles adjacent concerns ('validation is the separate scene_validate tool'). It also gives concrete conditional usage: guide=true for the guide, namespace for a namespace, search for ranked matches, op for a schema. This leaves little to inference.

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