Skip to main content
Glama

get_validation

Idempotent

Fetch and persist the validation report for a registered CSV contract preflight operation by operationId, reading the original run and matching output without creating or retrying runs.

Instructions

Read only the registered original run and bounded matching dataset/OUTPUT; persist local result. Unknown start stays HOLD. No run creation, retry, input repair, creator-revenue or import claim.

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": {
      "operationId": "<operationId>"
    },
    "name": "get_validation"
  }
}

Input Schema

NameRequiredDescriptionDefault
operationIdYes

Output Schema

NameRequiredDescriptionDefault
runIdYes
stateYes
limitsYes
reportYes
billingYes
operationIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

B3.1/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false, and the description correctly discloses the corresponding write behavior via 'persist local result', so there is no contradiction. It also surfaces a failure mode ('Unknown start stays HOLD') that annotations cannot express, which is genuine added context, though it leaves open what HOLD means operationally and what the caller should do next.

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

Conciseness3/5

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

Three short sentences with the read action front-loaded, so it is compact. But the wording is compressed to the point of obscurity ('bounded matching dataset/OUTPUT', 'creator-revenue or import claim'), so brevity is bought at the cost of comprehension rather than earned.

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?

An output schema exists, so return values need not be described, and the description does cover side effects and the HOLD case. The significant remaining gap is the sole input parameter and the absence of any positive usage routing against the many sibling get_*/start_* tools.

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% and the single parameter operationId is constrained only by a regex pattern. The description never mentions operationId, where it comes from, or whether it identifies the registered run — arguably the one piece of meaning a caller most needs. With one undocumented parameter, the description fails to compensate for the schema gap.

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

Purpose3/5

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

The description opens with a read operation against 'the registered original run and bounded matching dataset/OUTPUT', which signals retrieval of a validation run plus its data. However the phrasing is dense jargon ('bounded matching dataset/OUTPUT') and never plainly states 'retrieve a validation run and its result', nor does it distinguish itself from the sibling get_validation_summary.

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?

'No run creation, retry, input repair, creator-revenue or import claim' functions as exclusion guidance, steering the agent away from this tool for those intents and implicitly toward start_validation. But it is entirely negative: there is no positive statement of when to prefer this over get_validation_summary or get_contract_draft, and 'Unknown start stays HOLD' is not explained as a calling condition.

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