get_attrib_values

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 pagination behavior (check has_more, increment start), element-major ordering for float3 attributes, and the default page size. This goes beyond a simple 'read' statement and gives the agent actionable behavioral context. It doesn't mention error cases or performance characteristics, but the disclosed behaviors are substantial.

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 compact and front-loaded: the core behavior is stated in the first sentence, the alternative is named immediately, and the pagination detail is explained before the Args block. Every sentence earns its place, and the Args list is cleanly formatted.

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 read tool with 5 parameters and no output schema, the description covers the key operational details: pagination, element-major ordering, and the default count. It doesn't describe the exact return shape (e.g., JSON structure of has_more), but the description explicitly references has_more and start, which is enough for an agent to page through results. The main gap is not describing what the response object looks like, but the description's explicit mention of has_more and start mitigates that.

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. It does: it explains start as 'First element index to return', count as 'Max elements per page (default 200)', and attrib_class with the valid values 'point', 'prim', 'vertex', or 'detail'. This adds meaning beyond the bare schema, though it doesn't elaborate on node_path or attrib_name beyond their names.

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 clearly states the tool reads attribute values as a flat array with pagination, and explicitly contrasts it with sample_geometry for spot-checking. It names the specific resource (attribute values) and the operation (read), making it distinguishable from siblings like get_attrib_stats or sample_geometry.

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 explicit guidance: prefer sample_geometry for spot-checking a few values, and use get_attrib_values when you need a specific slice of one attribute. This directly tells an agent when to use this tool versus an alternative, which is exactly what usage guidelines should do.

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