Skip to main content
Glama

chat_cache_delete

DestructiveIdempotent

Deletes a temporary SQLite chat cache (metadata, blocks, FTS) by cacheId or platform+chatId without removing the provider chat; safe when rows are missing.

Instructions

Delete a temp SQLite cached chat (metadata, blocks, FTS). Does not delete the provider chat — use chats_delete for that. Identify via cacheId or platform+chatId. Idempotent on missing rows.

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_delete"
  }
}

Input Schema

NameRequiredDescriptionDefault
chatIdNoChat id when selecting cache by platform+chatId
cacheIdNoCache row id to delete
platformNoProvider id: chatgpt | grok | grok-x | claude | copilot | qwen | deepseek | perplexity

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.0.4
    • addedInput schema / properties / cacheId / description
      Added value: +"Cache row id to delete"
    • addedInput schema / properties / chatId / description
      Added value: +"Chat id when selecting cache by platform+chatId"
    • addedInput schema / properties / platform / description
      Added value: +"Provider id: chatgpt | grok | grok-x | claude | copilot | qwen | deepseek | perplexity"
  2. First observedv1.0.3

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description doesn't need to restate safety. It still adds real context beyond the annotations: the exact data classes destroyed (metadata, blocks, FTS index) and the scope boundary that the provider-side chat survives. It stops short of describing the return payload or what happens if only partially matching rows exist.

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 compact sentences, front-loaded with the destructive action and its scope before the disambiguation and identification hints. No filler or repeated information.

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 three-param idempotent delete with full schema coverage, the description covers action, scope boundary, and identification strategy. It is a little thin on outcome — what is returned or how success is confirmed when no row existed — though the idempotency note largely covers the behavioral risk.

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 both identifiers and the platform enum are already documented, which sets the baseline at 3. The description does add a genuine constraint by presenting cacheId and platform+chatId as two alternative identification paths, a relationship the flat schema does not express (no oneOf/anyOf).

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 — deleting a temporary SQLite cached chat — and scopes exactly what is removed (metadata, blocks, FTS). It explicitly contrasts with the sibling chats_delete so the two delete tools are distinguishable without opening either 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?

Names the alternative explicitly ("Does not delete the provider chat — use chats_delete for that"), which is the key routing decision between the two delete tools. It also tells the agent how to target the right row via cacheId or platform+chatId.

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