Indraft

find_duplicates

Read-only

Propose pairs of records that look like the same record, ranked by how alike their names are and whether they share a relationship. Works on companies, contacts, and a type this workspace defined. It PROPOSES only: nothing here merges anything, and the merge tools still require you to name both ids. Use it on a type with a declared identity too: the key cannot collide, so what is left to find is one person entered twice under two different keys. Walks the workspace a page at a time; pass the returned cursor to continue.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "objectType": "<objectType>"
    },
    "name": "find_duplicates"
  }
}

Input Schema

Name	Required	Description
`limit`	No	How many to return. The page bound is published in the schema call, and asking for more is refused rather than quietly truncated.
`cursor`	No	The opaque marker from the previous page. Store it and hand it back; do not parse it. A cursor is only ever emitted when another row really exists, so a page you were given is never empty.
`objectType`	Yes	What is being surveyed: a canonical type (company, contact), or the key of a type this workspace defined. A workspace's own type is surveyed on its first indexed text field, which is the name the search index holds for it.

Output Schema

Name	Required	Description	Default
`examined`	Yes
`candidates`	Yes
`nextCursor`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 1, 2026

addedInput schema / properties / cursor / description

Added value: +"The opaque marker from the previous page. Store it and hand it back; do not parse it. A cursor is only ever emitted when another row really exists, so a page you were given is never empty."

addedInput schema / properties / limit / description

Added value: +"How many to return. The page bound is published in the schema call, and asking for more is refused rather than quietly truncated."

addedInput schema / properties / objectType / description

Added value: +"What is being surveyed: a canonical type (company, contact), or the key of a type this workspace defined. A workspace's own type is surveyed on its first indexed text field, which is the name the search index holds for it."

First observedSep 1, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already declare readOnly and destructive false, but the description adds genuinely useful behavior: it 'PROPOSES only', paginates through the workspace with a cursor, and explains why a type with a declared identity can still have duplicates. This goes beyond the structured annotation fields without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Every sentence carries information: purpose, ranking logic, supported types, the read-only/merge distinction, the custom-type identity nuance, and pagination. It is front-loaded with the core purpose and has no fill.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only discovery tool, the description plus rich schema and annotations cover what it does, which types it applies to, how it paginates, and why it never merges. It is complete enough to invoke correctly without leaving major behavioral gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

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 limit, cursor, and objectType in detail. The description reinforces cursor pagination and objectType scope, but does not substantially add meaning beyond what the schema already supplies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description states a specific verb and resource: 'Propose pairs of records that look like the same record', and adds scope ('companies, contacts, a type this workspace defined') and the ranking criteria. It clearly separates itself from merge siblings by insisting 'nothing here merges anything'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context: this tool is the non-destructive duplicate *proposal* step, and merge tools require both ids, so it is intended to be used before merging. It does not explicitly name sibling alternatives or state excluded when-to-use cases, but the purpose and non-merge caveat provide strong signal.

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

All Indraft tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.