Skip to main content
Glama
Sign In
Polydev

Polydev

Official
by polydev-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

Ask models

ask_model
Read-only

Send a prompt to one or more AI models and return each labelled answer, using your default model set when none are specified.

Instructions

Send a prompt to one or more AI models and return each answer, labelled with what paid for it. With model or models, those models are asked. Without them, your default set is asked: sources on this machine first (your ChatGPT plan for OpenAI models when connected, then Claude Code and Codex under your own login, never the agent that called it), then models through Polydev with your own API keys, OpenRouter or Polydev free requests.

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": {
      "prompt": "<prompt>"
    },
    "name": "ask_model"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoOptional: one model ID to ask, for example a model shown by list_models.
modelsNoOptional: several model IDs to ask. Without model or models, your default set is asked.
promptYesThe prompt to send. Include the relevant code, errors and constraints.
user_tokenNoPolydev token (starts with pd_). Optional when POLYDEV_USER_TOKEN is set or you have run the login tool.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations cover safety (readOnlyHint=true, destructiveHint=false, openWorldHint=true), and the description adds real substance beyond them: answers are labelled by the payer, the default resolution order is spelled out, and it explicitly excludes the calling agent from the default set. It omits practical behavior an agent would want — cost/latency per call, what happens when one model in a set fails, or partial-failure semantics.

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?

Two sentences, front-loaded with the action and the return format, then the routing rules — no filler. The second sentence is long and comma-laden, which slightly hurts scannability of the default-set rules.

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 fan-out query tool with no output schema, the description covers what comes back (one answer per model, labelled by payer) and how the target set is resolved. Gaps remain around failure handling and whether calls incur cost, which matter given that some routes bill through a user plan or API keys.

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 an extra point by explaining the consequence of omitting model/models (the default set is used, in a defined precedence), which shapes how an agent should choose between the two parameters. It doesn't add anything about user_token or prompt that the schema doesn't already say.

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 specific verb and resource ('Send a prompt to one or more AI models') plus the return shape ('return each answer, labelled with what paid for it'). The 'one or more' framing plus the model/models routing makes clear this is the fan-out query tool, distinguishable from sibling tools like list_models and get_perspectives.

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 explicit branching guidance: pass model or models to target specific models, omit them and the default set is asked, with a stated precedence order (local sources first, then Polydev/OpenRouter). It stops short of naming alternatives such as get_perspectives for multi-lens queries or list_models for discovering IDs, so when-not-to-use is left implicit.

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

Deploy Server

Other Tools