Skip to main content
Glama

Export the leads (download link)

export_search
Read-onlyIdempotent

A download link for the search's leads as Excel (xlsx) or PDF: chosen kinds (default fit and partial), with the facts and the brief. The link works for one hour without signing in; give it to the user. [REST: GET /api/tasks/{id}/export.xlsx|pdf?kinds= (signed link /api/dl/{token})]

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": {
      "task_id": "<task_id>"
    },
    "name": "export_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindsNo
formatNoxlsx
task_idYesThe search id (task id), e.g. from list_searches or create_search.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes beyond them with high-value behavior: the link expires in one hour, it works without signing in, and it is a signed /api/dl/{token} URL. The security-relevant instruction to hand the link to the user is exactly the kind of context annotations cannot carry. It does not state whether generation is synchronous or how large exports behave.

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?

The purpose and the critical one-hour/no-sign-in constraint are front-loaded in the first clause, with content composition and the hand-off instruction following. The bracketed REST route is compact and only adds reference detail at the end, so no sentence is wasted.

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-parameter, no-output-schema tool that returns a link, the description covers what is returned, how long it lives, and who can use it, which is what an agent needs to act. Remaining gaps (synchronous vs. async generation, kind semantics) are small relative to the tool's simplicity.

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 only 33% (only task_id is documented in-schema), but the description compensates: it specifies the default kinds ('fit and partial') that the schema leaves unstated, and clarifies that format selects Excel or PDF. The meaning of the 'miss' kind value is left to the enum name alone, a minor remaining gap.

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 the concrete output (a download link for the search's leads) and the two formats (xlsx/PDF), plus what the file contains (facts, brief, chosen kinds). That is far more specific than the name alone. It does not explicitly contrast with the sibling export_outreach, so an agent must infer the distinction from 'the search's leads'.

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?

'give it to the user' is a real usage directive and the one-hour expiry implies a hand-off flow rather than server-side processing. However, there is no explicit when-not guidance and no named alternative (e.g. export_outreach for outreach data), so selection between export tools is only implied.

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