Skip to main content
Glama

tool_advisor

Read-onlyIdempotent

Which QL-API endpoint fits this task. POST a task description and get the ranked endpoint(s) that best match, each with a confidence label (high/medium/low). Deterministic keyword matching over this platform's own endpoint catalog, no LLM. Pairs with model_advisor (which itself is one of the recommendable endpoints, so a "which model" task surfaces it) - call them independently and chain the results yourself; optionally pass a prior model_advisor result's rationale in as context to bias matching.

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": "<task>"
    },
    "name": "tool_advisor"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskYesWhat you are trying to do.
toolsNoOptional allowlist - restrict matching to only these endpoints, by endpoint slug ("humanize") or MCP tool name ("humanize_text").
top_nNoHow many ranked endpoints to return. Default 1 = best match only.
contextNoOptional extra text to fold into matching - e.g. a prior model_advisor rationale, or more detail than fits in `task`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / tools / description
      Previous value: -"Optional allowlist - restrict matching to only these endpoint names."New value: +"Optional allowlist - restrict matching to only these endpoints, by endpoint slug (\"humanize\") or MCP tool name (\"humanize_text\")."
  2. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description adds real behavior beyond that: matching is deterministic keyword matching over the platform's own catalog with no LLM, and results carry high/medium/low confidence labels. It does not say what happens when nothing matches or how ties are broken, so it stops short of full disclosure.

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?

It is front-loaded with the purpose and the return shape before getting into the chaining advice, and every clause carries information. The dense nested parenthetical about model_advisor being a recommendable endpoint is harder to parse than it needs to be.

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 no output schema, the description does the necessary work of describing the return value (ranked endpoints each with a confidence label). Remaining gaps are minor: empty-result behavior and how the tools allowlist interacts with ranking are not addressed.

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 is 3; the description earns more by explaining what `context` is for (folding in a prior model_advisor rationale to bias matching) and by framing `task` as the thing being matched. It adds no guidance on `top_n` or the `tools` allowlist beyond what the schema already states.

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 opens with a precise question form ('Which QL-API endpoint fits this task'), then states the concrete verb and payload: 'POST a task description and get the ranked endpoint(s) that best match.' It explicitly distinguishes itself from the sibling model_advisor, so an agent can choose between them without reading either 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?

It names the alternative (model_advisor), states they should be called independently and chained by the caller, and gives a concrete condition for the optional `context` parameter (a prior model_advisor rationale). It also notes the self-referential case where a 'which model' task surfaces model_advisor itself, which is genuinely non-obvious routing guidance.

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.