Skip to main content
Glama

Keyed record snapshot differences

bpj_relation_snapshot_diff
Read-onlyIdempotent

Compare two snapshots with unique populated keys and report inserted, deleted or changed fields.

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>",
      "leftKey": "<leftKey>",
      "rightKey": "<rightKey>"
    },
    "name": "bpj_relation_snapshot_diff"
  }
}

Input Schema

NameRequiredDescriptionDefault
leftYes
rightYes
leftKeyYes
rightKeyYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds what the result classifies (insertions, deletions, changed fields), which is genuine behavioral context, but it says nothing about output structure, field-level granularity, or how key mismatches are handled when there is no output schema to fall back on.

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

Conciseness4/5

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

A single front-loaded sentence with no filler; every clause does work. It is efficient but so compressed that the key-format and uniqueness constraints are only suggested rather than stated, so the brevity costs some clarity.

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

Completeness3/5

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

Four required parameters, no output schema, and 0% schema coverage set a high bar. The description covers the purpose and the three result categories, but an agent still cannot tell the expected input encoding (JSON strings capped at 12000 chars), how key columns are referenced, or the shape of the returned diff. Adequate for selection, thin for correct invocation.

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

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%; the only parameter documentation is titles like 'Left records (JSON)' and 'Left key column'. The description refers to 'snapshots' and 'unique populated keys', which hints that leftKey/rightKey name key columns and that uniqueness is required, but it never states the JSON-string format, max lengths, or whether the keys are column names in that JSON. With a 0% coverage schema the description needed to carry this and largely does not.

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?

Names a specific verb ('compare') and resource ('two snapshots') plus the resulting classification (inserted, deleted, changed fields), which distinguishes it from the sibling bpj_summarize_unified_diff. It stops short of explicitly naming that sibling or stating the contrast, but the 'unique populated keys' qualifier effectively scopes it to keyed-record diffs.

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 only implied: the phrase 'with unique populated keys' signals the precondition that both sides must be keyed records, so an agent can infer this is not a generic text diff. There is no explicit when-to-use versus alternatives and no statement of what happens when keys are missing, duplicated, or non-unique.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.