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

With no annotations, the description carries the full behavioral burden; it does disclose a key trait ('Returns part_id and attributes only; no geometry') and a prerequisite source. However, it says nothing about pagination behavior despite a page_token parameter, nor about auth, limits, or mutation risk (implicitly read-only but never stated).

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?

Dense, labeled, and front-loaded with the When/Prerequisites/Next ordering; no wasted sentences. It reads like a compact routing card rather than prose, which is appropriate here.

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 return values need not be explained, and the routing context is solid. The remaining shortfall is the unexplained parameter set (notably the opaque guidance_handle and pagination via page_token), which leaves an agent guessing on invocation details.

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% across 6 parameters, so the description must compensate. It clarifies part_layer's origin and implies a filter capability, but leaves filter, part_ids, page_token (pagination!), max_results, and the opaque guidance_handle entirely undocumented, which is a substantial 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 '[Tier 2 — Part Metadata]' tag combined with 'enrich or filter parts before build, or inspect attributes without geometry' states a specific verb+resource and clarifies the scope is attributes, not geometry. It is distinguishable from build tools via the 'Next' routing, though it never names a direct alternative among the many selection/part siblings.

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 explicit 'When:', 'Prerequisites:', and 'Next:' structure names the trigger conditions, the required part_layer source (ezt://part-layers), and the downstream tools (direct_build, configure_map). It clearly says when to use it but does not distinguish it from get_part_selection or request_part_selection, which sound closely related.

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