Skip to main content
Glama

get_memory_evidence

Read-onlyIdempotent

Retrieves a memory's raw evidence chain and evidence profile so an agent can quote original session text and cite its sources. Read-only; missing or pruned evidence returns an empty chain.

Instructions

Get the raw-evidence chain a memory was distilled from (its L0 trace rows), plus its evidence profile. Read-only grounding: lets an agent quote the original session text and name its sources. Use add_evidence to write a new relation or source — this tool only reads the existing chain. Missing or pruned evidence yields an empty chain rather than a write; requires agent auth when the agent has a registered key.

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_id": "<memory_id>"
    },
    "name": "get_memory_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
api_keyNoAPI key for agent authentication (required if agent has a registered key)
agent_idNoID of the requesting agentunknown
memory_idYesThe memory whose raw-evidence chain (L0 trace rows) to expand

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and idempotentHint, so safety is covered; the description still adds behavior the annotations cannot express — missing or pruned evidence returns an empty chain rather than an error or write, and the call requires agent auth when a key is registered. It stops short of describing chain ordering, size, or payload shape, which the annotations don't cover either.

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?

Front-loaded with the core action and return payload, then purpose, then the write-alternative exclusion, then edge-case/auth notes. Four compact sentences with no filler; the auth clause slightly duplicates the schema but is short enough not to bloat.

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?

No output schema exists, yet the description compensates by naming the return payload ('raw-evidence chain ... plus its evidence profile') and the empty-chain edge case. Auth and error behavior are also covered, leaving only finer return-shape details unspecified for a simple three-parameter read tool.

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%, so memory_id and api_key semantics are already documented in the schema ('The memory whose raw-evidence chain (L0 trace rows) to expand'). The description paraphrases the auth requirement but adds no format or identifier-convention detail beyond the structured fields, so baseline 3 applies.

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

Purpose5/5

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

States a concrete verb and resource — get the raw-evidence chain (L0 trace rows) plus evidence profile for a memory. The parenthetical 'L0 trace rows' pins down exactly what is returned, which no sibling tool name suggests, so an agent can distinguish it from search_memory or review_memory without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names the alternative and the boundary: 'Use add_evidence to write a new relation or source — this tool only reads the existing chain.' It also states the grounding use case ('quote the original session text and name its sources'), so both when-to-use and when-not-to-use are covered.

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