Skip to main content
Glama

chat_cache_update_block

Update a single cached conversation block to revise content or bump its revision, and optionally resync that turn from the live browser tab.

Instructions

Update one cached block (bumps revision) or resync that turn from the live tab via resyncFromHost. Prefer for surgical cache edits; use chat_cache_append to add turns, chat_cache_sync to refresh the whole chat. Local cache only unless resyncFromHost needs the bound browser.

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": {
      "turnIndex": "<turnIndex>"
    },
    "name": "chat_cache_update_block"
  }
}

Input Schema

NameRequiredDescriptionDefault
roleNoOptional role override for the block
chatIdNoChat id when selecting cache by platform+chatId
cacheIdNoCache row id containing the block
contentNoReplacement content when not resyncing from host
platformNoProvider id: chatgpt | grok | grok-x | claude | copilot | qwen | deepseek | perplexity
turnIndexYesZero-based turn index of the block to update
resyncFromHostNoWhen true, refresh this turn from the live provider tab instead of content

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv1.0.4
    • addedInput schema / properties / cacheId / description
      Added value: +"Cache row id containing the block"
    • addedInput schema / properties / chatId / description
      Added value: +"Chat id when selecting cache by platform+chatId"
    • addedInput schema / properties / content / description
      Added value: +"Replacement content when not resyncing from host"
    • addedInput schema / properties / platform / description
      Added value: +"Provider id: chatgpt | grok | grok-x | claude | copilot | qwen | deepseek | perplexity"
    • addedInput schema / properties / resyncFromHost / description
      Added value: +"When true, refresh this turn from the live provider tab instead of content"
    • addedInput schema / properties / role / description
      Added value: +"Optional role override for the block"
    • addedInput schema / properties / turnIndex / description
      Added value: +"Zero-based turn index of the block to update"
  2. First observedv1.0.3

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare the mutation is non-destructive and non-idempotent; the description usefully adds that each call bumps a revision (consistent with idempotentHint=false) and that the operation is local-cache-only unless resyncFromHost requires the bound browser. That last clause is a mild tension with openWorldHint=false, but it reads as describing a locally bound browser rather than an external service, so it is disclosure rather than contradiction. It stops short of saying what happens when the block or cache row is missing.

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?

Three short sentences, each carrying a distinct payload: capability, sibling routing, and execution environment. The primary action is front-loaded and no sentence is redundant.

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 7 parameters, full schema coverage, no output schema and non-destructive annotations, the description supplies the mode distinction and the routing an agent needs. Minor gaps remain around failure behavior (missing block, missing cache row) and the cacheId versus platform+chatId selection rule, but these are edge-case rather than blocking.

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 would be 3, but the description adds genuine meaning beyond the schema: resyncFromHost replaces content for that turn and requires the bound browser, implying the content and resyncFromHost parameters are mutually exclusive paths. It does not clarify when to use cacheId versus platform+chatId, which is the one selection ambiguity left.

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?

States a specific verb and resource ('Update one cached block') plus the alternate mode ('resync that turn from the live tab via resyncFromHost'). It also explicitly distinguishes itself from chat_cache_append and chat_cache_sync, so an agent can route correctly without reading sibling schemas.

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

Usage Guidelines5/5

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

Gives an explicit preference rule ('Prefer for surgical cache edits') and names the two alternatives with the condition that selects each: append to add turns, sync to refresh the whole chat. When-to-use and when-not-to-use are both covered.

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