Skip to main content
Glama
io.github.kushvinth/crowbar

io.github.kushvinth/crowbar

cb_models

Query an offline LLM catalog to compare context windows, per-million-token pricing, and capabilities by provider or search term.

Instructions

LLM catalog: context window, price per M tokens, capabilities.

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": "cb_models"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryNo
providerNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.5

TDQS

C2.4/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full disclosure burden. It states what fields exist but not whether the call is read-only, how results are ordered or paginated, how the default limit of 40 behaves, or what happens when no query matches — all material for a catalog endpoint with a capped result set.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The single fragment is front-loaded and free of padding, so there is no waste to trim. The brevity is under-specification rather than conciseness, though, and a fragmentary list of fields is a weak structure for an entry-point discovery tool.

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?

The task is simple — a filtered catalog read — and the description does convey the payload's content, which is the core need. With three undocumented parameters, no annotations, and no output schema, an agent still lacks enough to build a correct filtered call without trial and error.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for all three parameters (limit, query, provider), so the description must compensate and does not. It never explains what 'query' matches against (model name, provider, capability), whether 'provider' is exact-match or substring, or why the limit is capped at 200.

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

Purpose3/5

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

The description names the resource ('LLM catalog') and enumerates the fields it exposes (context window, price per M tokens, capabilities), which is more specific than the name alone. However, it omits a verb and never distinguishes the tool from lookup-oriented siblings such as cb_product or cb_search, so the agent must infer that this is a browse/list endpoint.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no exclusion of alternatives, and no mention of prerequisites. The agent is left to guess whether this is for discovering models, filtering by provider, or resolving a model name before calling another tool.

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