Skip to main content
Glama

Recall Memories

recall_memories
Read-onlyIdempotent

Retrieve relevant long-term memories for a query with deterministic ranking by BM25, salience, tier weight, feedback utility, and freshness.

Instructions

Retrieve relevant memories ranked deterministically by BM25, salience, tier weight, feedback utility, and temporal freshness.

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_memories"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoOptional retrieval context mode override.
limitNoMaximum number of memories to return.
queryYesSearch query to match against stored memories.
namespaceNoNamespace filter (omit to search default or all).
token_budgetNoMaximum token budget for returned memories.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered without the description. The description does add real value by disclosing the deterministic ranking factors (BM25, salience, tier weight, feedback utility, temporal freshness), which tells the agent results are consistently ordered. It says nothing about pagination, how token_budget interacts with limit, or what happens when the budget truncates results.

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?

A single front-loaded sentence with no filler; the resource and the ranking mechanism come first. It is efficient but under-sized for a tool with five parameters and six context modes, so a little more would not have been waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Annotations and the schema carry most of the burden, and no output schema exists so return format need not be explained. Still missing for a retrieval tool are the semantics of the six mode values (the schema only says 'retrieval context mode override') and how limit interacts with token_budget, which an agent must guess.

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 all five parameters including the six-value mode enum and the token_budget default are already documented in structured data. The description adds no parameter-level meaning beyond the schema, so the baseline of 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?

States a specific verb and resource ('Retrieve relevant memories') plus the exact ranking signals used, so the agent knows this is a ranked search over stored memory rather than a context build or a mutation. It does not name any sibling to distinguish itself from, e.g. build_context or forget_memory, leaving that separation implicit.

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

Usage Guidelines2/5

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

There is no when-to-use guidance: nothing says when to prefer this over build_context, search_code, or list_agent_wings, and nothing explains when a mode override or namespace filter is appropriate. The agent must infer usage entirely from the tool name and schema.

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