Skip to main content
Glama

Store key relationships

store_big_meta
Destructive

Store key relationships so Tolgee can use translations of related keys as context during machine translation, producing more consistent results. Keys that appear near each other in source code (e.g. on the same page or component) should be stored as related.

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": {
      "relatedKeysInOrder": "<relatedKeysInOrder>"
    },
    "name": "store_big_meta"
  }
}

Input Schema

NameRequiredDescriptionDefault
branchNoOptional: branch name
projectIdNoID of the project. Can be left out when the credential is bound to one project: a project API key, or an OAuth token for one project.
relatedKeysInOrderYesList of related keys in the order they appear together

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / projectId / description
      Previous value: -"ID of the project (required for PAT, auto-resolved for PAK)"New value: +"ID of the project. Can be left out when the credential is bound to one project: a project API key, or an OAuth token for one project."
  2. First observed

TDQS

B3.2/5.0
Behavior2/5

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

Annotations declare destructiveHint=true, but the description never says what is destroyed — whether an existing relationship set is replaced, merged, or appended. It does explain the purpose of the stored data (MT context), but for a destructive mutation the missing replacement semantics is a significant gap.

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 sentences, front-loaded with the purpose and followed by the usage rule, with no redundant wording. Everything present earns its place, though it is arguably too short for a destructive mutation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive write tool with a nested array parameter and no output schema, the description omits critical facts: whether prior relationships are overwritten, what happens on repeated calls, and how projectId/branch affect the stored set. An agent could invoke it correctly syntactically but not predict its side effects.

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 every parameter is already documented, including the ordering meaning of relatedKeysInOrder. The description only adds the notion of what 'related' means (same page/component), which clarifies selection rather than adding format or constraint detail beyond the schema.

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 names a specific verb and resource ('store key relationships') and explains the downstream effect (related-key context during machine translation). It implicitly separates itself from tag_keys/update_key by tying relationships to source-code proximity, but never names a sibling or explicitly contrasts with tagging.

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?

It gives a selection rule for content ('keys that appear near each other in source code ... should be stored as related'), which is useful guidance on what to send. It says nothing about when to call this tool versus update_key or tag_keys, nor about prerequisites such as project/branch scoping.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.