Skip to main content
Glama
Sign In

Andru

by io.github.geter-andru
OverviewDiscussionsAdmin

Tell Andru what you sell

set_product_context
DestructiveIdempotent

Use this when the person tells you what they sell, or Andru doesn't know their product yet. Send their company website (Andru reads it and remembers the product) or a short product description, once. Andru turns it into a product description and, from that, their first ICP: who fits and who doesn't (about 3 minutes). Every later call uses it. Call with no arguments to see what Andru has saved.

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": "set_product_context"
  }
}

Input Schema

NameRequiredDescriptionDefault
websiteNoYour company website, e.g. acme.com. Andru reads the homepage once.
verticalNoOptional: the industry you sell into.
targetRoleNoOptional: the buyer role you target, e.g. CFO.
productDescriptionNoOr: what your product does and who it is for (2-3 sentences).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations declare destructiveHint=true and idempotentHint=true, but the description never explains what is overwritten or lost when context is re-set — that gap matters for a destructive, open-world tool. It does add genuinely useful context beyond annotations: the ~3-minute processing time, that the website is read only once, and that every later call depends on this stored context.

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?

Four tight sentences with zero redundant restatement of the title, and the trigger condition is front-loaded. Slightly dense with parenthetical asides, but every sentence carries decision-relevant information.

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?

Given no output schema, the description does the necessary work by telling the agent what is produced (product description plus first ICP, in ~3 minutes) and how to inspect saved state. What's missing is any warning about the destructive overwrite implied by destructiveHint=true.

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 100%, so baseline would be 3, but the description adds meaning the schema doesn't: website and productDescription are presented as alternatives ('...or a short product description'), and the modes are framed as either/or. It still doesn't say how website and productDescription interact if both are supplied.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: capture the company's product (via website or description) and derive the first ICP from it. It is clearly distinguishable from siblings like get_icp_profile or preview_company because it is the write-side entry point that creates the stored context. An agent knows exactly what this tool accomplishes without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit trigger conditions: 'Use this when the person tells you what they sell, or Andru doesn't know their product yet.' It also documents the no-argument read mode ('Call with no arguments to see what Andru has saved'), covering both the write and read paths. The 'once' instruction prevents redundant re-sends.

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