Skip to main content
Glama
Sign In
ContextOS

ContextOS

by aftabkh4n
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

recall

Search stored memories by meaning and keywords to surface past decisions and gotchas before answering questions, ranked by relevance, recency, and importance.

Instructions

Read-only. Searches stored memories by meaning and keywords, ranked by relevance, recency and importance. Use it before answering questions about past decisions or gotchas. Returns a JSON array of {id, type, content, score}; content is cut to 300 characters.

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
kNoMaximum results, 1 to 20 (default 5)
queryYesWhat to look for, in plain words
scopeNocurrent (default): this workspace. global: every workspace on this machine; results include the workspace name.current
typesNoOnly these types: note, decision, gotcha, todo, skill. Ignored when scope is global.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.2.5
    • changedInput schema / properties / k / description
      Previous value: -"Max results, 1-20"New value: +"Maximum results, 1 to 20 (default 5)"
    • changedInput schema / properties / query / description
      Previous value: -"Search query"New value: +"What to look for, in plain words"
    • changedInput schema / properties / scope / description
      Previous value: -"current or global"New value: +"current (default): this workspace. global: every workspace on this machine; results include the workspace name."
    • changedInput schema / properties / types / description
      Previous value: -"Types filter"New value: +"Only these types: note, decision, gotcha, todo, skill. Ignored when scope is global."
  2. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

No annotations exist, so the description carries the full burden and does well: it opens with "Read-only" to establish the safety profile and discloses the ranking factors. It also states the return shape and the 300-character truncation of content, which is a real behavioral caveat an agent would otherwise miss.

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?

Four short sentences, front-loaded with the read-only constraint, then purpose, then usage trigger, then return contract. Nothing is redundant and every sentence carries information the 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 no annotations and no output schema, the description compensates well by declaring read-only behavior and describing the returned array structure and truncation. Only minor gaps remain, such as ranking tradeoffs or result-size behavior beyond the schema-declared k bound.

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 coverage is 100%, so the four parameters are already fully documented in the input schema, making 3 the baseline. The phrase "by meaning and keywords" adds a hint that the query is matched both semantically and lexically, but scope, types, and k are left entirely to 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?

"Searches stored memories by meaning and keywords, ranked by relevance, recency and importance" states a specific verb (search) and resource (memories) plus the ranking model. It implicitly separates itself from the write-side siblings (remember, remember_skill) by being explicitly read-only, though it never names them.

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?

"Use it before answering questions about past decisions or gotchas" gives clear situational guidance that tells the agent exactly when recall is the right call. It stops short of naming alternatives or exclusions, but the trigger condition is unambiguous.

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