find_nested

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

With no annotations, the description fully discloses behavior: returns composed world coordinates, rotation, scale, and mirror flag; explains that filters apply after traversal and do not prune; reveals the time budget (segundos default 25) and the partial=true fallback, including that partial results are incomplete. This is excellent transparency.

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 efficiently structured in three short paragraphs, each with a distinct purpose: purpose, usage/performance, and timeout behavior. Every sentence carries value, with clear emphasis (PASA, NO) and no filler.

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 complex tool with 13 parameters and an output schema, the description covers core functionality, usage recommendations, performance characteristics, and partial-result semantics. It does not explain every parameter, but the presence of an output schema reduces the need to describe return values, making this sufficiently complete for most use cases.

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?

Although schema coverage is 0%, the description adds meaning to near_x/near_y/radius (spatial pruning), segundos (time budget), and implies layer/type filters exist but do not reduce traversal. However, with 13 parameters, many remain unexplained (e.g., limit, detail, max_depth, text_contains, attribute_value), so the description only partially compensates for the schema gap.

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 searches inside XREF and nested blocks, returning composed world coordinates, rotation, scale, and mirror state. It explicitly claims to be the only way to locate entities two levels deep, distinguishing it from sibling search tools.

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?

Provides explicit guidance to pass near_x/near_y/radius when location is known, explains that layer/type filters do not reduce traversal, and warns about performance without a spatial window. It clearly implies when to use this tool (for nested content) but does not explicitly name alternatives or exclusions, so it falls short of a 5.

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