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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description goes further by describing result shape (top 3 candidates per label, each with a score), the empty-list meaning ('no existing item matched'), the algorithm set, and that it is deterministic with no LLM call — meaningful behavior an agent cannot read from the schema.

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?

Three tight sentences, front-loaded with the action and followed by the return contract and the determinism guarantee. No filler, no restatement of the title.

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 does the necessary work of describing the return contract: up to three scored candidates per label and an empty list as the no-match signal. It does not specify whether results are keyed or ordered by input label, which would matter for bulk calls with up to 500 labels, leaving a small gap.

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 baseline is 3. The description adds a concrete example of what a 'label' is (a row label from a parsed file), but says nothing about model_id, whose user-scoped versus model-scoped key distinction lives entirely in 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?

States a specific verb and resource: resolves free-text labels to existing item UIDs of a model. It explicitly names the input domain (e.g. row labels of a parsed file) and the matching methods, so an agent can distinguish it from siblings like layerz_parse_file or layerz_read without opening the schema.

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 implied by the phrase 'row labels of a parsed file', which hints at a parse-then-match workflow, but no sibling tool is named and no when-not or prerequisite condition is given (e.g. must the model already exist, should this precede a mapping write?). The agent must infer the workflow position.

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