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

Annotations already declare readOnly, idempotent, and non-destructive, so safety is covered; the description reinforces this with 'Read-only' and adds operational context the annotations don't: the 200-item batch cap and the two-part result structure (exact vs. scored matches). It stops short of describing rate limits, pagination, or what happens when the memory is empty.

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 usage directive is front-loaded ahead of the mechanical detail, and every sentence contributes something. The trailing 'Read-only' duplicates the annotation, and the parentheses around the items example make the middle dense, but there is 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?

With an output schema present, the description needn't enumerate return fields, and it still summarizes `exact` and `matches` usefully. Combined with the workflow placement and reuse rule, an agent has enough to call this correctly in the extraction pipeline; only the `memory` and `top_k` semantics remain unaddressed.

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 carries the burden, and it does well for `items` — spelling out the object's shape (kind/name/class_name) and the max of 200. However, `memory` and `top_k` are never explained, leaving two of three parameters undocumented in both schema and prose.

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 — check whether candidate names already exist in the memory — and frames the operation as a batch dedupe/resolution step rather than a search. This clearly separates it from siblings like semantic_search, list_objects, or merge_objects.

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?

Gives explicit timing and cardinality: 'call ONCE per document during extraction, after drafting candidate entities and before emitting the final JSON.' It also states the decision rule — reuse returned canonical names, create only names with no hits — which is exactly the when/when-not guidance an agent needs.

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