Skip to main content
Glama

workbench_record_finding

Records an evidence-linked finding for an analysis case, capturing severity, description, recommendation, and verification level so reproduced defects are documented with provenance and reproduction details.

Instructions

Record a caller-authored, evidence-linked finding. reproduced requires an actual completed project check and reproduction details. Do not classify inference or fake-provider tests as real-provider verification.

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": {
      "case_id": "<case_id>",
      "title": "<title>",
      "category": "<category>",
      "severity": "<severity>",
      "verification": "<verification>",
      "description": "<description>",
      "recommendation": "<recommendation>",
      "evidence_records": "<evidence_records>"
    },
    "name": "workbench_record_finding"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleYes
case_idYes
categoryYes
severityYes
descriptionYes
limitationsNo
reproductionNo
verificationYes
recommendationYes
evidence_recordsYes
reproducer_recordNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3/5.0
Behavior3/5

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

Annotations already declare this is a non-read-only, non-destructive, open-world write, so the safety profile is covered. The description adds the norm that findings must be evidence-linked and that verification claims are constrained, which is real behavioral context. It omits whether findings are mutable after creation, whether the case must be open, and whether evidence_records must pre-exist.

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 sentences with no filler and the core action front-loaded. However, at this brevity for an 11-parameter write tool it reads as under-specification rather than disciplined concision.

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

Completeness2/5

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

An 11-parameter, 8-required mutation tool with zero schema descriptions and no output schema needs far more than three sentences. Nothing tells the agent what a case_id must reference, what categories mean, or what happens on success, which leaves an agent to guess on most required fields.

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% across 11 parameters, so the description must carry the full explanatory burden. It only touches two of them indirectly ('evidence-linked' for evidence_records, 'reproduction details' for reproduction) and leaves case_id, title, category, severity, limitations, description, recommendation, and especially reproducer_record entirely unexplained — including the relationship between reproduction and reproducer_record.

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?

States a specific verb and resource: 'Record a caller-authored, evidence-linked finding.' That is distinguishable from read/analyze siblings, but the description never differentiates this from workbench_report, which sounds like an adjacent write path for the same kind of content.

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?

It gives one concrete usage rule — 'reproduced' requires an actual completed project check, and inference or fake-provider tests must not be labeled real-provider verification. That is useful, but it only addresses one enum value; there is no guidance on when to choose hypothesis vs source-reviewed, or when to record a finding here versus routing it through workbench_report.

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