Skip to main content
Glama

Build Research Record

build_research_record
Read-onlyIdempotent

Converts host-gathered web sources for a dish into a structured provenance record with extracted ingredients, techniques, sensory descriptors, uncertainty, and confidence.

Instructions

Convert host-researched source facts into a typed provenance record. Returns a structured research record with extracted ingredients, techniques, sensory descriptors, uncertainty, and confidence. Use when the host AI has gathered web sources for a dish. Pass dishName, query, and sources from the host research results.

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": {
      "dishName": "<dishName>",
      "query": "<query>",
      "sources": "<sources>"
    },
    "name": "build_research_record"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYes
sourcesYes
dishNameYes

Output Schema

NameRequiredDescriptionDefault
queryYes
sourcesYes
dishNameYes
createdAtYes
confidenceYes
uncertaintyYes
extractedFactsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.2

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive closed-world behavior, so the safety profile is covered. The description adds useful context that this is a pure transformation step over host-supplied sources and summarizes the returned fields. It does not disclose handling of unreliable or sparse sources, deduplication, or error behavior when sources are malformed.

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?

Three sentences, front-loaded with the transformation and the return shape, then the usage condition and parameter hint. Efficient, though describing the return payload is partly redundant given an output schema exists.

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?

Output schema presence relieves the need to explain return values and annotations cover safety, so the remaining burden is input structure. Given a 3-parameter schema with nested required objects and zero field-level documentation, the description should say more about how to construct sources; that gap is the main incompleteness.

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%, so the description carries the burden, but it only names the three parameters (dishName, query, sources) without explaining them. Critically, the nested source object — required title, url, sourceType, accessedAt, reliability, extractedFacts — and the reliability enum semantics are documented nowhere, and the description does not compensate.

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: convert host-researched source facts into a typed provenance record, with a stated output (ingredients, techniques, sensory descriptors, uncertainty, confidence). This separates it from validate_research_record and extract_research_findings in spirit, but neither sibling is named, so the boundary is inferred rather than declared.

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?

"Use when the host AI has gathered web sources for a dish" gives a clear precondition for invocation, and it tells the agent the inputs must come from prior host research rather than being invented here. It stops short of naming alternatives or stating when not to use it (e.g. after a record already exists).

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