Fuzzy-dedupe a list of records into clusters of likely-duplicate entities. Blocks by normalized token prefix, scores with Jaro-Winkler + token-set matching (exact on email/phone), unions matches above threshold, and returns a merged canonical record per cluster with a confidence score. Deterministic, no LLM calls.
| Name | Required | Description | Default |
|---|---|---|---|
| options | No | ||
| records | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully discloses the algorithm: blocking by normalized token prefix, scoring with Jaro-Winkler and token-set matching, exact match on email/phone, union above threshold, and deterministic output. This provides complete transparency about the tool's behavior.
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 two sentences long, packed with essential information about the tool's purpose and algorithm. It is front-loaded with the main action and does not contain any unnecessary words or details.
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?
Given the complexity of a dedup algorithm and no output schema, the description explains the return format (merged canonical record per cluster with confidence) and the major algorithmic steps. Minor missing details like error handling or constraints (maxItems) slightly reduce completeness, but the description is largely sufficient for agent invocation.
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 must add value. It refers to 'list of records' for the records parameter and mentions 'threshold' in the algorithm, but does not explicitly describe the 'keys' sub-parameter in options. The description adds moderate context beyond the schema, but lacks full param coverage.
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 performs fuzzy-deduplication of records into clusters of likely duplicates, returning merged canonical records with confidence scores. It provides specific details on the algorithm (blocking, scoring) that distinguish it from any potential generic dedup tool.
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 description explicitly explains when to use the tool (for fuzzy dedup) and describes its algorithmic behavior. It lacks explicit exclusions or alternatives, but the deterministic and no-LLM-call nature gives clear context. With no sibling tools provided, the guidance is adequate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Only one tool exists, so there is no possibility of confusion between tools. The single tool has a clear and distinct purpose.
With only one tool, naming consistency is trivially maintained. The verb-based name 'resolve' fits a common naming pattern.
A single tool for entity resolution is borderline; the server's scope is narrow, but 1 tool falls outside the typical 3-15 range and may feel thin for more complex workflows.
The single tool covers the entire entity resolution workflow (blocking, scoring, merging, returning canonical records) with no obvious gaps for its stated domain.