Skip to main content
Glama
Sign In
mcp-context-window

mcp-context-window

by donliggett
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

context_recall

Retrieve relevant stored entries for a query, packed to fit your token budget. Ask for what you need instead of reading the whole session.

Instructions

Retrieve the most relevant stored entries for a query, packed to fit a token budget. This is the main way to get memory back into your working context: ask for what you need rather than reading the whole session. Pinned entries are always included. Omit the query to get the most recent entries instead.

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": {
      "session_id": "<session_id>"
    },
    "name": "context_recall"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of entries
queryNoWhat you are looking for. Omit for most-recent ordering.
session_idYesSession identifier. Reuse the same string across a task to accumulate memory.
budget_tokensNoMaximum tokens of entries to return

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral burden. It discloses useful traits: results are 'packed to fit a token budget,' pinned entries are always included, and omitting the query switches to most-recent ordering. These go beyond the schema and help an agent predict behavior.

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 sentences with no filler. The primary action is front-loaded, followed by usage context and two key behavioral caveats. Every sentence earns its place.

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 4-parameter tool with no annotations and no output schema, the description covers the main use case, query omission, pinned entries, and token budgeting. It does not specify the return shape or how limit and budget_tokens interact, but it is largely sufficient for an agent to invoke the tool correctly.

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 coverage is 100%, so the baseline is 3. The description adds value by clarifying query omission behavior ('Omit the query to get the most recent entries instead') and explaining the token-budget intent behind budget_tokens. It does not detail the interaction between limit and budget_tokens, but it compensates beyond 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?

The description opens with a specific verb and resource: 'Retrieve the most relevant stored entries for a query.' It also distinguishes itself from siblings by calling itself 'the main way to get memory back into your working context' and contrasting with 'reading the whole session.'

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 clearly states when to use the tool: when you need memory back into context, ask for what you need rather than reading the whole session. It also explains the no-query variant for recent entries. However, it does not explicitly name alternatives or state when not to use this tool versus siblings like context_open or doc_search.

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