Skip to main content
Glama

Kubeez

pick_model

Read-onlyIdempotent

Scope: none (any authenticated key). Resolve ONE model for a job, with priced alternates and the reason anything was excluded. PREFER THIS over reading the whole get_models catalog when you are choosing a model: the video catalog alone is 141 rows, and comparing them by eye is how a job lands on a model that costs several times what an equally capable one does. Describe the job, not a model: modality, how many images / videos / audios you will attach, duration_s, spoken_language, wants_recurring_character, nsfw, aspect_ratio. DESCRIBE THE INPUTS HONESTLY - pass images=1 when the user attached one image. A wrong count returns a model that cannot take the file, and the attachment gets ignored. Returns primary (the QUALITY pick for that lane), alternates led by the CHEAPEST capable model with its price, rejected naming what could not do the job and why, and cheaper_option when the cheap route is materially less than the primary - say BOTH numbers in your plan card when it is. tier='cheapest' inverts it and returns the cheapest capable model as primary; tier='quality' is the default behaviour stated explicitly. If the user NAMED a model, pass it as user_named_model: it is returned verbatim with its price and a capability_warning if the inputs do not fit. This tool NEVER substitutes a different family or tier for a model the user asked for. A spoken name ('treblo', 'kling 4 flash') that matches exactly ONE id resolves to it and says so in resolved_from; one that matches several returns did_you_mean, so ask. This does not generate anything and costs no credits; follow it with estimate and generate_media.

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": "pick_model"
  }
}

Input Schema

NameRequiredDescriptionDefault
nsfwNo
tierNovalue
audiosNo
imagesNo
videosNo
modalityNovideo
documentsNo
duration_sNo
aspect_ratioNo
spoken_languageNonone
user_named_modelNo
wants_recurring_characterNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, but the description adds materially: 'costs no credits', the exact return shape (primary/alternates/rejected/cheaper_option), the 'did_you_mean' ambiguity path, 'resolved_from', and the strong 'NEVER substitutes a different family or tier' guarantee. It loses a point because 'does not generate anything' largely restates readOnlyHint rather than adding new information, and the mismatch between the description's stated tier default ('quality') and the schema default ('value') leaves the actual default behavior slightly ambiguous.

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 scope and purpose before the mechanics, and most sentences carry distinct operational information (counts, tier inversion, named-model passthrough, ambiguity handling). It is verbose, though, with capitalized emphasis ('DESCRIBE THE INPUTS HONESTLY', 'QUALITY pick', 'CHEAPEST capable model') and some redundancy around the no-cost / no-generation point that could be tightened.

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

Completeness5/5

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

For a 12-parameter, zero-schema-documentation tool, the description supplies the auth scope, the cost model, the return contract, the ambiguity path, the no-substitution rule, and the follow-up tools. An output schema exists, so the return-field explanations are extra rather than required; nothing an agent needs to call this correctly is missing.

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 description coverage is 0% across 12 parameters, so the description must compensate, and it largely does: it enumerates the job-shape inputs (modality, image/video/audio counts, duration_s, spoken_language, wants_recurring_character, nsfw, aspect_ratio), plus tier and user_named_model, and it explains the consequence of a wrong count ('a model that cannot take the file, and the attachment gets ignored'). It falls short of a 5 because 'documents' is never mentioned and no accepted values are given for the string parameters (modality, aspect_ratio, tier), which have no enums in 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 opening states a specific verb and resource: 'Resolve ONE model for a job, with priced alternates and the reason anything was excluded.' It also explicitly distinguishes itself from the sibling catalog reader: 'PREFER THIS over reading the whole get_models catalog when you are choosing a model.' An agent can tell exactly what this does and why it exists alongside get_models.

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 (get_models), the condition that selects it ('when you are choosing a model'), the sequencing ('follow it with estimate and generate_media'), and the tier override semantics ('tier="cheapest" inverts it'). It also handles the user-named-model branch and says to ask when 'did_you_mean' comes back, so the when/when-not paths are all covered.

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.

Resources