class_info

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

No annotations are supplied, so the description carries the full burden. It does useful work by disclosing the return payload and the error behavior ('unknown classes say so'), plus case-insensitive matching, but it never states this is a read-only lookup or addresses the batch size implied by the schema's 500-item cap.

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 compact clauses: first what you get back, then how to address it. Front-loaded with the payload, zero filler, and the unknown-class behavior is appended in a short trailing phrase rather than padding the lead.

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 one-parameter, annotation-free query tool with no output schema, the description covers both the accepted input forms and the returned fields, which is the bulk of what an agent needs. The minor gaps are the missing read-only framing and the undocumented 500-item batch limit.

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, and it does: it explains that the single 'names' array accepts class names (case-insensitive) or model paths/model ids. That is real meaning beyond the bare 'array of strings' schema, with only the min/max item limits left to the schema.

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 names a specific resource (class/model dimensions) and enumerates exactly what is returned: size [X, Y, Z] in meters, clipping and collision box, radius, flags, and shape-raster existence. It is clearly distinguishable from siblings like query_objects or world_objects, though it never states that distinction 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?

Usage is only implied: the agent can infer this is the lookup for class geometry, and the accepted lookup keys (class name, model path, model id) are given. There is no explicit 'use this when' or any comparison against alternatives such as world_info or query_objects, so routing relies on inference.

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