Skip to main content
Glama

Build Reconstruction Dossier

build_reconstruction_dossier
Read-onlyIdempotent

Assembles a structured food or drink memory dossier from collected memory, a research plan, and optional facts, separating source-backed evidence from inferences before generating a nostalgia cue.

Instructions

Build an evidence-separated food or drink memory dossier from user memory, research plan, and optional researched or inferred facts. Returns a structured dossier separating source-backed facts from inferences. Use when assembling the full evidence base before generating a nostalgia cue. Pass memory from collect_food_memory, researchPlan from plan_dish_research, and optionally researchedFacts.

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": {
      "memory": "<memory>",
      "researchPlan": "<researchPlan>"
    },
    "name": "build_reconstruction_dossier"
  }
}

Input Schema

NameRequiredDescriptionDefault
memoryYesStructured output from collect_food_memory
researchPlanYesStructured output from plan_dish_research
inferredFactsNoExplicit inferences that are not direct source facts
researchedFactsNoSource-backed facts gathered by the host AI or research tools

Output Schema

NameRequiredDescriptionDefault
titleYes
confidenceYes
hypothesesYes
evidenceLedgerYes
whatToAskFamilyYes
recreationStrategyYes
nostalgiaCriticalElementsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.2

TDQS

A3.8/5.0
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 and side-effect profile is fully covered. The description adds the meaningful semantic that output is evidence-separated into facts vs inferences, but beyond that it does not describe validation behavior, failure modes, or how conflicting evidence is handled.

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 what and the return semantics, then usage, then parameter sourcing. Dense and largely waste-free; the phrase 'user memory, research plan, and optional researched or inferred facts' slightly duplicates the following sentence.

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?

Given a deeply nested input schema, a declared output schema, and full annotations, the description supplies the pipeline position and the evidence-separation contract that structured fields cannot express. It is nearly complete, with only the boundary against sibling build_* tools left unaddressed.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3; the description goes beyond it by naming the provenance of each argument and marking researchedFacts/inferredFacts as optional versus the two required inputs. It does not explain how inferredFacts interact with researchedFacts during separation.

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 gives a specific verb and resource ('Build an evidence-separated ... memory dossier') and states the core output property (separating source-backed facts from inferences). It stops short of distinguishing this from similarly named siblings such as build_memory_receipt or build_research_record, so an agent must infer the boundary from the input provenance alone.

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?

It states a clear trigger ('Use when assembling the full evidence base before generating a nostalgia cue') and maps each input to its producing upstream tool (memory from collect_food_memory, researchPlan from plan_dish_research). There are no explicit when-not conditions or exclusions against the adjacent build_* tools.

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