Skip to main content
Glama
Sign In

Substrate

by co.trysubstrate
OverviewDiscussionsAdmin

Memory evidence

memory_evidence
Read-onlyIdempotent

Return the source excerpts one memory was built from, by the handle memory_search returned: up to limit excerpts (default 5, at most 20), plus the original source text when raw is true. Pass share to read a handle from someone else's share.

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": {
      "handle": "<handle>"
    },
    "name": "memory_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
rawNo
limitNo
shareNoOptional. Omit it to read your own memory (the normal case). Only pass a share handle exactly as memory_shares listed it, or as a shared result's share.handle; never invent one.
handleYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds useful operational detail (default 5, hard cap of 20, raw returns original source text) but says nothing about failure behavior for an invalid or expired handle.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core action and scoped by the handle's origin, with no filler. Every clause carries information the caller needs.

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?

With no output schema, the description properly describes what comes back (excerpts, plus raw source text when raw is true) and the default/cap behavior. Missing only error-path guidance, which is a minor gap for a read-only retrieval tool.

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 only 25%, so the description must compensate, and it does: it defines limit's default and ceiling, explains that raw controls inclusion of the original source text, and clarifies that share reads a handle from another user. Only handle's format and the share pattern constraints are left to the schema.

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 specific verb and resource ('Return the source excerpts one memory was built from') and ties the input to a named sibling ('by the handle memory_search returned'), which lets an agent distinguish it from memory_search and memory_expand without opening any schema.

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?

Gives clear prerequisites (you must have a handle from memory_search) and names the alternate mode (pass share to read someone else's share). It stops short of saying when not to use this tool, e.g. that a different sibling is better when no handle is available.

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

All Substrate toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources