Skip to main content
Glama

invalidate_mcp_cache

Idempotent

Invalidate cached discovery data for an external MCP server after its tools change, or clear all tenant MCP caches by omitting the server UUID.

Instructions

Invalidate cached discovery for an external MCP server after its available tools change.

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": "invalidate_mcp_cache"
  }
}

Input Schema

NameRequiredDescriptionDefault
mcp_server_idNoSpecific MCP server UUID; omit to invalidate all MCP caches for the tenant

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.2.4
    • changedInput schema / properties / mcp_server_id / description
      Previous value: -"UUID do MCP server específico (omitir para invalidar todo o cache do tenant)"New value: +"Specific MCP server UUID; omit to invalidate all MCP caches for the tenant"
  2. First observedv0.1.0

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already cover the key traits: not read-only, idempotent, non-destructive, open-world. The description adds only that the target is cache/discovery state rather than server config, which is some useful framing. It doesn't disclose whether caches repopulate lazily on next discovery, whether in-flight requests are affected, or whether the operation fails if the server doesn't 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?

One sentence, front-loaded with the action and object, with zero filler. Nothing is redundant or buried.

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-optional-parameter cache-invalidation tool with rich annotations and no output schema, the description is nearly sufficient: purpose, target, and trigger are all present. The remaining gap is outcome semantics — what the caller should expect afterward (cache miss, forced re-discovery) is not stated.

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?

With a single optional parameter and 100% schema description coverage, the schema already explains that omitting mcp_server_id invalidates all tenant caches. The description contributes nothing about that parameter or its tenant-wide fallback, so the baseline of 3 applies.

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?

Uses a specific verb ("Invalidate") and a precise resource ("cached discovery for an external MCP server"), and adds the causative condition (tool-set change). This distinguishes it from update_mcp_server or test_mcp_server implicitly, but it never names those siblings, so the differentiation is left to inference.

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?

Gives a concrete trigger: call it "after its available tools change." That is clear when-to-use context. However, there is no when-not guidance and no alternatives named — e.g. it doesn't say whether other server mutations (URL or credential changes) also warrant invalidation, or whether test_mcp_server should be used to verify afterward.

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

Deploy Server

Other Tools