Skip to main content
Glama
Sign In
Dawnmere

Dawnmere

by Hadeva-Dev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Recall from memory

recall
Read-only

Retrieve what was saved to shared memory earlier—preferences, projects, decisions or people—by searching on meaning and keywords. Use when an answer depends on prior context from any connected AI app.

Instructions

Use this when the answer may depend on something the user told you or another of their AI apps before: their preferences, projects, decisions or people. Searches the user's memory by meaning and keywords.

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": {
      "query": "<query>"
    },
    "name": "recall"
  }
}

Input Schema

NameRequiredDescriptionDefault
kNoHow many memories at most (default 8).
queryYesWhat to look for, in plain words.
sectionNoKeep one part of memory, if the user names one.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

The annotations already establish that this is a safe read (readOnlyHint=true) against a closed corpus (openWorldHint=false). The description adds behavior the annotations cannot express: retrieval is hybrid (by meaning and keywords) and the corpus is cross-app user memory, which changes how an agent should phrase a query. It says nothing about ranking or empty-result behavior, keeping it below 5.

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 tight sentences with no filler: the triggering condition comes first and the operational behavior second. Every clause carries information an agent 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 three simple parameters, no nested objects, full schema coverage, and annotations covering the safety profile, the description supplies enough to call the tool correctly. The only gap is that there is no output schema, so nothing explains what a recalled memory looks like or how empty results are signaled.

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%, with each parameter (query, k, section) documented in the schema itself, so the baseline is 3. The description's 'by meaning and keywords' hints at how to phrase the query but adds no parameter-level syntax or defaults beyond the 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?

The description names a specific verb and resource: it 'searches the user's memory by meaning and keywords.' That is clearly distinct from the sibling write/delete tools (remember, forget) and the status tool, although the differentiation is implicit rather than stated.

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 gives an explicit triggering condition: use it 'when the answer may depend on something the user told you or another of their AI apps before,' and enumerates the relevant memory types (preferences, projects, decisions, people). It does not name alternatives or say when not to use it, so it falls short of a 5.

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

Deploy Server

Other Tools