Skip to main content
Glama

Save Query

save-mcp-query

Use when the user wants to save discovery or enrichment results for later — e.g., "save these results" or "I want to come back to this list."

Saves MCP results as a thin wrapper query visible in the app UI. Data should contain at minimum a domain column, plus any custom columns to preserve (similarity scores, MCP-computed fields, etc.).

Valid action values: ['discover', 'segment', 'contacts', 'append', 'match']

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": {
      "input": "<input>"
    },
    "name": "save-mcp-query"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputYesRequest model for saving result rows as a thin-wrapper saved query. Shared by the REST `POST /queries/save-results` endpoint and the `save-mcp-query` MCP tool so the payload shape stays identical.
contextNoWhy you are calling this tool, in a few words. No names or emails.
llm_modelNoYour model id, or "unknown".
conversation_idNoThe conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics.

Output Schema

NameRequiredDescriptionDefault
_mcp_instructionsNoServer-issued metadata for this conversation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / conversation_id
      Added value: +{
      +  "description": "The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics.",
      +  "type": "string"
      +}
    • addedOutput schema / properties
      Added value: +{
      +  "_mcp_instructions": {
      +    "description": "Server-issued metadata for this conversation.",
      +    "properties": {
      +      "conversation_id": {
      +        "description": "The server-issued conversation identifier.",
      +        "type": "string"
      +      }
      +    },
      +    "type": "object"
      +  }
      +}
  2. Changed2 schema fields changed
    • addedInput schema / properties / context
      Added value: +{
      +  "description": "Why you are calling this tool, in a few words. No names or emails.",
      +  "type": "string"
      +}
    • addedInput schema / properties / llm_model
      Added value: +{
      +  "description": "Your model id, or \"unknown\".",
      +  "type": "string"
      +}
  3. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Adds real behavioral context beyond the annotations: the results become a persisted 'thin wrapper' query that is visible in the app UI, and the row shape to preserve. It does not address the non-idempotent hint — i.e., whether re-saving the same query_name creates a duplicate or fails — which is the main behavioral risk an agent would want disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the trigger condition and examples, then moves to mechanics and payload expectations — a sensible order with little filler. The final line restating the five valid action values duplicates the schema enum and could be cut.

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?

With a full schema, full description coverage, and an output schema, the description covers purpose, invocation trigger, and payload shape well. Remaining gaps (duplicate-name behavior, any row/column limits) are modest rather than blocking.

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 the nested input object documents query_name, action, data, tags, query_params, and domain_column already. The description adds only a light gloss on the data payload (minimum domain column plus custom columns like similarity scores), and it repeats the action enum verbatim rather than explaining what each action implies. Baseline 3 is appropriate.

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?

States a specific verb and resource ('Saves MCP results as a thin wrapper query') and clarifies the resulting artifact is visible in the app UI, which separates it from raw data-append tools. It does not explicitly differentiate itself from close siblings such as save-exclusion-list or list-saved-queries, so an agent must infer the boundary.

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?

Opens with an explicit triggering condition ('Use when the user wants to save discovery or enrichment results for later') and backs it with two concrete user utterances. It gives no when-not guidance or prerequisites (e.g., that results must already exist from a prior discovery/enrichment call).

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.

Resources