Skip to main content
Glama
Sign In

Andru

by io.github.geter-andru
OverviewDiscussionsAdmin

Build an asset

generate_asset

Building the material a step needs, often what the champion carries into rooms the person won't be in: use this when the person picked an asset from Andru's catalog (find it with list_assets), e.g. 'Board Presentation', 'Buying Committee Navigation'. Built from everything Andru knows about their company and saved to their Andru library. Takes up to a few minutes: returns a job_id; call get_asset with it to receive the asset as markdown.

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": {
      "asset": "<asset>"
    },
    "name": "generate_asset"
  }
}

Input Schema

NameRequiredDescriptionDefault
assetYesThe asset name from list_assets.
prospectCompanyNoFor a prospect asset (Pre-Call Intelligence Brief, Deal Reengagement Strategy, Personalized Cost of Inaction One-Pager): the company it is for.
prospectContactNoFor a prospect asset: the person it is for, name and title.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false), the description discloses the key non-obvious behavior: this is an asynchronous long-running generation that takes minutes, returns a job_id rather than the content, and persists the artifact to the Andru library. That async contract is exactly what an agent needs to avoid misusing the tool.

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?

The critical facts — the precondition, the async job_id return, and the get_asset follow-up — are front-loaded and the piece is only two sentences. The opening clause is a bit meandering ('rooms the person won't be in'), costing some tightness but not comprehension.

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 an async generation tool with no output schema, the description covers the input source, latency expectation, the job_id contract, and the retrieval step. Remaining gaps — what happens if the job fails, and whether cancel_job applies to the returned job_id — are real but secondary.

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 schema already documents all three parameters including the prospect-only variants. The description adds only the contextual note that the asset string must come from Andru's catalog (list_assets) and that it is built from company knowledge; it does not explain when prospectCompany/prospectContact become mandatory.

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 concrete resource to create (material/assets like 'Board Presentation' or 'Buying Committee Navigation') and distinguishes this build step from list_assets (finding the name) and get_asset (retrieving the result). The framing sentence 'building the material a step needs' is somewhat jargon-heavy, but the examples make the output type unambiguous.

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?

It states the triggering condition explicitly — use this when the person has picked an asset from Andru's catalog — and routes the agent to list_assets to obtain the asset name and to get_asset afterwards. No when-not-to-use case or failure guidance is given, which keeps it just short of the top band.

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

All Andru toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources