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

Annotations already declare readOnlyHint and non-destructive, so the safety profile is covered. The description adds genuinely useful behavior: determinism ('no LLM call'), the candidate-per-label cap of 3, the scoring, and the meaning of an empty candidate list. It omits any note on ordering or score range, keeping it short of a 5.

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 tightly packed sentences with the purpose front-loaded and zero filler. The parentheticals and clause list make it dense but still readable; nothing is wasted.

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?

With no output schema, the description carries the return-value burden and does it well: candidate count, methods, scoring, and empty-list semantics are all stated. Minor gaps remain (score scale, ranking order), but an agent has enough to call and interpret it.

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%, so the schema already documents both parameters, including model_id's scoping rules. The description clarifies what a label resolves to and the result shape per label, but adds little parameter-level meaning beyond the schema, matching the baseline 3.

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 precise verb+resource: resolving free-text labels to existing item UIDs of a model. It further specifies the mechanics (top 3 candidates across exact_uid, exact_name, slug, and Levenshtein fuzzy matching, each scored), which no sibling tool does, so an agent can distinguish it from layerz_parse_file or layerz_validate_model immediately.

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?

Anchors the use case concretely with 'e.g. row labels of a parsed file,' implying this follows a parse step and precedes item creation/update. It does not name explicit alternatives or exclusions, so it falls short of a full when-to-use/when-not statement.

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