dump_scene

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

With readOnlyHint=true already covering scene safety, the description adds real context: it writes a file to disk, the file is grep-friendly, and it returns the path rather than the data. It does not warn about output size on large scenes or overwrite behavior of a prior dump.

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 short sentences, front-loaded with the action and format, followed by content scope and the follow-up step. Minor noise from leading indentation but no wasted sentences.

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?

An output schema exists, so the return value need not be explained, and the description still clarifies it is a file path examined via Read. For a 5-parameter tool with full schema coverage this is nearly complete, only lacking guidance on output size or whether it overwrites existing dumps.

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 100%, with root, max_depth, filter_types, property_filter and include_properties each documented in the schema. The description adds nothing about parameters, so baseline 3 applies — the schema does all the work.

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: dumps the full scene graph into a prim-block text file with prims, properties, bounding boxes and transforms. An agent can tell this produces a file artifact rather than an in-memory result, distinguishing it from get_scene_tree or get_prim_properties, though no sibling is named explicitly.

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 gives a clear operational recipe: call this, then use the Read tool to inspect specific parts of the grep-friendly file. That implicitly frames it as the choice for full-scene inspection, but it never says when to prefer export_prim_as_file or get_scene_tree instead.

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