chat-export-server

Overview Schema Source Related Servers Discussions Admin

chat_cache_read

Read-onlyIdempotent

Read cached chat blocks from local SQLite by turn range, block ID, or full-text query without opening a browser, so you can retrieve stored conversation excerpts quickly after a sync.

Instructions

Read cached chat blocks from local SQLite by turn range, blockId, or FTS query without hitting the browser. Prefer after chat_cache_sync/chat_outline; use chat_read when the cache may be cold and a live fetch is OK. Identify the copy via cacheId or platform+chatId.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "chat_cache_read"
  }
}

Input Schema

Name	Required	Description
`query`	No	FTS5 search query over cached turn text
`chatId`	No	Chat id when selecting cache by platform+chatId
`blockId`	No	Specific cached block id to return
`cacheId`	No	Cache row id from a previous sync/outline
`endTurn`	No	Exclusive end turn index
`maxChars`	No	Hard cap on returned characters (200-200000)
`platform`	No	Provider id: chatgpt \| grok \| grok-x \| claude \| copilot \| qwen \| deepseek \| perplexity
`startTurn`	No	Inclusive start turn index

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedv1.0.4Nov 11, 2026

addedInput schema / properties / blockId / description
```
Added value: +"Specific cached block id to return"
```

addedInput schema / properties / cacheId / description

Added value: +"Cache row id from a previous sync/outline"

addedInput schema / properties / chatId / description

Added value: +"Chat id when selecting cache by platform+chatId"

addedInput schema / properties / endTurn / description
```
Added value: +"Exclusive end turn index"
```

addedInput schema / properties / maxChars / description

Added value: +"Hard cap on returned characters (200-200000)"

addedInput schema / properties / platform / description

Added value: +"Provider id: chatgpt | grok | grok-x | claude | copilot | qwen | deepseek | perplexity"

addedInput schema / properties / query / description

Added value: +"FTS5 search query over cached turn text"

addedInput schema / properties / startTurn / description
```
Added value: +"Inclusive start turn index"
```

First observedv1.0.3Nov 11, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so safety is covered. The description adds genuinely new behavioral context: the data is local SQLite, no browser hit occurs, and the cache is only populated after a sync/outline. It stops short of describing what happens when the cache is empty or how results are shaped, so it is strong but not exhaustive.

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 tight sentences with zero filler: purpose first, prerequisite and alternative second, addressing mode last. Every clause carries actionable information and nothing is repeated from the schema.

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 an 8-parameter, no-required, no-output-schema read tool, the description covers purpose, prerequisite ordering, fallback, and addressing strategy. The remaining gaps (return shape, behavior on cache miss) are minor and partly implied by the chat_read fallback guidance.

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 per-parameter descriptions already carry the baseline. The description adds the selection relationships the schema leaves implicit: the three ways to slice cached blocks, and that the cache copy is identified by either cacheId OR platform+chatId as alternatives. That is useful routing logic beyond the flat property list.

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 (read cached chat blocks from local SQLite) and names the three selection modes (turn range, blockId, FTS query). It explicitly contrasts itself with chat_read (live fetch) and chat_cache_sync/chat_outline, so an agent can distinguish it from siblings without opening any schema.

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 ordering rule ("Prefer after chat_cache_sync/chat_outline") and an explicit alternative with its selecting condition ("use chat_read when the cache may be cold and a live fetch is OK"). Both the when and the when-not are stated rather than inferred.

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