Skip to main content
Glama

Build Memory Receipt

build_memory_receipt
Read-onlyIdempotent

Create a portable, evidence-bounded receipt for a food-memory reconstruction session, including the evidence ledger, hypotheses, next questions, and first taste test for checkpointing or finalization.

Instructions

Create a portable evidence-bounded receipt for a food-memory reconstruction session. Returns a Memory Receipt with the evidence ledger, hypotheses, next questions, and first taste test. Use when finalizing or checkpointing a reconstruction. Pass memory from collect_food_memory and optionally researchPlan and cue from generate_minimum_viable_nostalgia.

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>"
    },
    "name": "build_memory_receipt"
  }
}

Input Schema

NameRequiredDescriptionDefault
cueNoStructured output from generate_minimum_viable_nostalgia when a first test has been produced
memoryYesStructured output from collect_food_memory
researchPlanNoStructured output from plan_dish_research
assistantTextNoFinal assistant-facing summary to include in the receipt

Output Schema

NameRequiredDescriptionDefault
titleYes
statusYes
evidenceYes
createdAtYes
shareCardNo
hypothesesYes
assistantSummaryYes
nextBestQuestionsYes
firstTinyTasteTestNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.2

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered; the description adds composition context by enumerating the receipt's sections and the 'evidence-bounded' framing. The only soft spot is that 'checkpointing' hints at persistence while the tool is declared read-only — the description never clarifies that it only returns an object rather than storing one.

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 artifact definition before the contents and the usage/provenance guidance; nothing is redundant. 'Portable evidence-bounded' is mild jargon but earns its place by conveying the receipt's constraint.

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?

An output schema exists, so the brief return summary is sufficient, and the description correctly identifies the one required input plus the two optional upstream artifacts for a heavily nested 4-parameter tool. The only unresolved question an agent could have — whether the receipt is persisted or merely returned — is not addressed.

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

Parameters3/5

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

Schema description coverage is 100% and each parameter already carries a 'Structured output from X' description, so the description's guidance on where memory/cue/researchPlan come from largely restates the schema. It adds pipeline ordering ('pass memory ... optionally ...'), but no new meaning about content or shape. Baseline 3 for a fully documented schema.

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: 'Create a portable evidence-bounded receipt' and names the artifact's contents (evidence ledger, hypotheses, next questions, first taste test). It is distinct from the collection/generation siblings, but it never contrasts itself with the other build_* tools (build_reconstruction_dossier, build_research_record), which an agent routing on name similarity would want.

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 finalizing or checkpointing a reconstruction' gives a clear triggering condition, and the description specifies the input provenance (memory from collect_food_memory; researchPlan and cue from generate_minimum_viable_nostalgia). It stops short of saying when NOT to use it or when build_reconstruction_dossier is the better choice.

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