Skip to main content
Glama

recall

Search previous work memories by keywords or questions to retrieve facts, decisions, tasks, and fixed errors; call at session start for context.

Instructions

Search memories of previous work by keywords/question. Returns facts, decisions, tasks and fixed errors. Call at session start!

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
modeNo"index" = one line per hit with id; fetch details with get_memoryfull
limitNoMaximum number of results
queryYesQuestion or keywords, e.g. "why did the build fail"
projectNoOptional — limit to one project (path or name)
maxCharsNoOptional — cut the result at N characters to fit the context window

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.16.1
    • addedInput schema / properties / limit / description
      Added value: +"Maximum number of results"
    • changedInput schema / properties / maxChars / description
      Previous value: -"Opsional — potong hasil pada N karakter (budget context window)"New value: +"Optional — cut the result at N characters to fit the context window"
    • changedInput schema / properties / project / description
      Previous value: -"Opsional — batasi ke satu proyek (path/nama)"New value: +"Optional — limit to one project (path or name)"
    • changedInput schema / properties / query / description
      Previous value: -"Pertanyaan atau kata kunci"New value: +"Question or keywords, e.g. \"why did the build fail\""
  2. First observed

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full behavioral burden. It does disclose the return contents, which is genuinely useful, but says nothing about read-only nature, scope of the memory store, result ordering, or what an empty result means. Safety profile and side effects are left entirely implicit.

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 short sentences with the action front-loaded and zero filler. The imperative call-to-action at the end is compact and memorable, though the terse style leaves little room for the routing detail that is missing.

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?

For a five-parameter search tool with a fully documented schema and no output schema, the description is close to sufficient: it states what is searched and what is returned. The main residual gap is disambiguation from sibling retrieval tools, which the definition does not attempt.

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 the schema already explains mode, limit, project, and maxChars in detail. The description only reinforces the query parameter as a "keyword/question" and implies keyword matching, adding no meaning beyond structured fields. Baseline 3 applies.

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?

Names a specific verb and resource ("Search memories of previous work") and enumerates what comes back (facts, decisions, tasks, fixed errors). It stops short of distinguishing itself from retrieval siblings such as get_memory or related, so an agent still has to guess which memory tool to pick.

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

Usage Guidelines3/5

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

"Call at session start!" is an explicit timing cue, which is useful, but there is no when-not guidance and no routing to alternatives. An agent reading this cannot tell when to prefer this over related, get_memory, or project_context, all of which plausibly return memory content.

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