Skip to main content
Glama
dataparity

dataparity

dataparity_diff_tables

Compare two tables across databases to report added, removed, and modified rows, schema differences, a risk verdict, and where changes concentrate.

Instructions

Compare two tables and report what changed. Works across different databases: both sides compute the same canonical row hash, so only hashes are compared, never raw data. Returns added, removed and modified rows, schema differences, a risk verdict, and the segments of data where the changes concentrate.

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": {
      "left": "<left>",
      "right": "<right>",
      "left_table": "<left_table>",
      "right_table": "<right_table>",
      "key_columns": "<key_columns>"
    },
    "name": "dataparity_diff_tables"
  }
}

Input Schema

NameRequiredDescriptionDefault
leftYesThe left source name.
rightYesThe right source name.
whereNoA WHERE expression applied to both sides.
formatNoOutput format. Defaults to json.
sampleNoCompare only a sample of rows. The result is marked as sampled.
columnsNoColumns to compare. Defaults to every column the two tables share.
left_tableYesThe table on the left.
key_columnsYesColumns used to match rows across the two sides.
max_changesNoMaximum number of row changes to return. Defaults to 100.
right_tableYesThe table on the right.
max_attributionsNoMaximum number of attribution segments to return. Defaults to 5.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.0

TDQS

A3.8/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden, and it does substantial work: it discloses the hash-only comparison model, that raw data is never read, and the full catalog of returned artifacts (added/removed/modified rows, schema differences, risk verdict, attribution segments). It leaves unstated that the operation is read-only in effect and says nothing about cost or runtime on large tables.

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?

Three sentences, each carrying new information: the operation, the cross-database hash mechanism that explains the privacy/perf profile, and the return contents. The core purpose is front-loaded and there is no filler.

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

Completeness4/5

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

With 11 parameters, no annotations, and no output schema, the description is doing the right things: it explains the comparison mechanism and enumerates the return contents, which substitutes for the absent output schema. It is slightly thin on cross-database edge cases (type mismatches, missing keys, behavior of where across dialects) for a tool of this complexity.

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 all 11 parameters are already documented in structured fields, and the description need only reinforce. It adds light meaning to output-shaping parameters by mentioning the 'risk verdict' and the 'segments of data where the changes concentrate,' but contributes nothing new about key_columns, where, sample, or format beyond the schema.

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

Purpose4/5

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

The description opens with a specific verb and resource: 'Compare two tables and report what changed,' which is unambiguous about the operation. It does not name or distinguish itself from any sibling (list_tables, describe_table, list_sources), though the comparison function is distinct enough that an agent can partition it by topic alone.

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

Usage Guidelines3/5

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

Usage is implied by the operation itself and the note that it 'works across different databases,' which tells the agent the appropriate scenario. There is no explicit statement of when not to use it, no prerequisite or cost/permission guidance, and no named alternative for single-table inspection tasks.

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