mcp-context-window

context_update

Manage context entries by pinning important ones to survive compaction or deleting incorrect ones to clean up recall.

Instructions

Pin, unpin, or delete a single entry by its id. Pin what must survive compaction; delete what turned out to be wrong, so it stops polluting recall.

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>",
      "entry_id": "<entry_id>"
    },
    "name": "context_update"
  }
}

Input Schema

Name	Required	Description
`delete`	No	Remove the entry from recall
`pinned`	No	Set or clear the pin
`entry_id`	Yes	Entry id, as shown in recall output
`session_id`	Yes	Session identifier. Reuse the same string across a task to accumulate memory.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Aug 23, 2026

TDQS

A4.4/5.0

Behavior4/5

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

With no annotations available, the description carries the burden of disclosure. It explicitly mentions that pinning affects compaction survival and that deletion removes from recall, which are non-obvious behavioral consequences. It does not specify edge cases like simultaneous pin+delete, but this is acceptable for a simple mutation tool.

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 sentences with zero wasted words. The action verb and primary resource are front-loaded, and the purpose/effect follows immediately. It is perfectly sized for quick comprehension.

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 tool with two required and two optional booleans, the description adequately covers what the tool does and why. It doesn't mention the session_id parameter, but the schema's description ('Reuse the same string across a task to accumulate memory') covers that. There is no output schema, so no return-value description is needed. The only minor gap is a lack of explicit mention of unpinning behavior when pinned=false, but that is inferred.

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?

The schema covers all four parameters with descriptions, so the baseline is 3. The description adds meaningful context by explaining the purpose of each action beyond the schema's dry definitions ('survive compaction', 'stops polluting recall'), which helps agents understand the semantic intent of the boolean flags.

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 clearly states the action (pin, unpin, or delete) on a specific resource (a single entry by id), with a concise rationale for each. It distinguishes itself from siblings like context_compact and context_recall by focusing on single-entry mutation rather than bulk operations or retrieval.

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 provides clear guidance on when to pin versus delete ('Pin what must survive compaction; delete what turned out to be wrong'), which serves as an implicit usage test. It does not explicitly contrast with sibling tools like context_compact, but the context is sufficient for most agent decisions.

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

Deploy Server