Skip to main content
Glama
Sign In

Andru

by io.github.geter-andru
OverviewDiscussionsAdmin

Ask an Andru specialist

consult_agent

Any step, when no other tool fits: use this when the person asks an open question for one of Andru's domain experts. Gets a domain-scoped answer in natural language (it may call lookup tools; tools that cost money must be called directly). One turn per call; pass prior turns as history to continue. Use module to pick the expert (e.g. 'market-clarity', 'deal-acceleration', 'due-diligence', 'portfolio-ops').

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": {
      "module": "<module>",
      "message": "<message>"
    },
    "name": "consult_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
moduleYesWhich domain agent to consult (e.g. 'market-clarity', 'due-diligence', 'portfolio-ops').
historyNoOptional prior turns: [{ role, content }]. At most 10 turns of 2,000 characters each.
messageYesYour question / request for the agent (up to 4,000 characters).
quoteIdNoOptional: the quote_id from quote, to pay the quoted price (held for 30 minutes).
idempotencyKeyNoOptional: any unique string for this call. Retrying with the same key returns the first result and never charges twice.
maxAmountCentsNoOptional: the most this call may cost, in cents. If the price is higher, nothing runs and nothing is charged.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / maxAmountCents
      Added value: +{
+  "description": "Optional: the most this call may cost, in cents. If the price is higher, nothing runs and nothing is charged.",
+  "minimum": 0,
+  "type": "integer"
+}
  2. First observed

TDQS

A3.8/5.0
Behavior3/5

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

The description adds useful behavior beyond the annotations: answers are natural language, one turn per call, prior turns go in `history`, and the agent may call lookup tools. However, it does not explain that this consult can itself involve pricing, what `quoteId` and `maxAmountCents` imply for charges, or how `idempotencyKey` protects retries, which matters given `readOnlyHint=false`.

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 description is compact and front-loads the fallback usage rule, then covers behavior and expert selection. It is appropriately sized, though the phrase "Any step, when no other tool fits" is slightly fragmented and the paid-tool caveat is a bit ambiguous.

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

Completeness3/5

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

For a six-parameter, open-world consult tool with no output schema, the description sufficiently explains the answer format and turn/history model. It is less complete on the financial workflow around `quoteId`, `maxAmountCents`, and `idempotencyKey`, which are important for correct invocation despite being described in the schema.

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 description coverage is 100%, so all six parameters are already documented in the schema itself. The description adds module examples and clarifies that `history` continues prior turns, but does not add meaning for `quoteId`, `idempotencyKey`, or `maxAmountCents` beyond the schema.

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?

The description states a specific fallback role: consulting one of Andru's domain experts for an open question and returning a natural-language answer. It also distinguishes this tool from siblings by saying to use it only when no other tool fits and to select the expert via `module`.

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 gives a clear usage condition — open questions for a domain expert when no other tool fits — and explains that paid tools must be invoked directly rather than through this agent. It does not name specific sibling alternatives, but the fallback rule is explicit enough to guide selection.

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