Skip to main content
Glama

refresh_history_index

Refresh the persistent graph index and in-memory keyword cache manually; use rebuild=true to recreate the derived graph database while leaving agent history files unchanged.

Instructions

Manually refresh the persistent graph index and in-memory keyword cache.

rebuild=true deletes and recreates the derived graph database. It never modifies any agent's history files.

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": "refresh_history_index"
  }
}

Input Schema

NameRequiredDescriptionDefault
rebuildNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full disclosure burden, and it does deliver the most important fact: rebuild=true deletes and recreates the derived graph database. The added reassurance that history files are never modified is genuinely valuable for a destructive-sounding operation, but cost, duration, and whether searches are degraded while the rebuild runs are all unstated.

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 short sentences, action stated first and the parameter consequence immediately after, with no filler. Every clause earns its place, including the safety boundary in the final line.

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 single-boolean maintenance tool with an output schema that can document the response, this is close to sufficient: it names the refreshed artifacts and the destructive scope of rebuild. The only meaningful omission is operational context such as expected duration or whether the rebuild should be avoided mid-session.

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 0% and the only structured hint is a boolean titled 'Rebuild' defaulting to false, so the description must compensate and does: it explains what rebuild=true actually does and what it leaves untouched. The non-rebuild (cache-only) path is only implied by the phrase 'and in-memory keyword cache' rather than spelled out as the default behavior.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Manually refresh') and two concrete resources ('persistent graph index', 'in-memory keyword cache'), so an agent knows exactly what state is being rebuilt. It does not distinguish itself from plausible siblings like sync_memory or search_graph, leaving the agent to infer which index-refresh path applies.

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

Usage Guidelines3/5

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

'Manually' implies this is the on-demand escape hatch rather than an automatic path, which hints at when to reach for it. However, there is no explicit trigger condition (e.g. stale or missing search results) and no stated alternative such as sync_memory, so the when/when-not decision is left implicit.

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