Skip to main content
Glama

Free2AITools

by com.free2aitools
OverviewDiscussionsAdmin

free2aitools_select_model

Filter the Free2AITools catalog by declared hardware/license metadata and return FNI-ranked candidate entries. USE WHEN you have concrete constraints (VRAM, params, license, context length, local-runnability) and want candidates narrowed by them. Constraints are metadata/heuristic filters over stored fields, NOT verified compatibility analysis, model inference, or model execution; this tool does not decide for you and is not an inference router. The caller is responsible for the final selection. Results are FNI-ranked, never paid placement, with no billing. Read-only, no side effects. Use free2aitools_search for unconstrained keyword discovery, or free2aitools_rank for keyword ranking without metadata filters.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
taskYesTask name or natural language description (e.g. "text-generation", "code assistant", "image classification")
limitNoMax entries returned (1-20, default 5)
explainNoInclude per-entry fni_summary (factual FNI factor/spec facts) and caveats in the response (default true)
constraintsNoHardware and license filters (all optional)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / constraints / properties / can_run_local / description
      Previous value: -"Only models that can run locally"New value: +"Heuristic local-runnability filter based on stored metadata such as model size and GGUF indicators. Does not verify actual runtime compatibility on the caller hardware or framework."
    • changedInput schema / properties / constraints / properties / ollama_compatible / description
      Previous value: -"Only models runnable via Ollama"New value: +"Heuristic filter on stored metadata (GGUF indicators). Does not verify actual Ollama runtime compatibility on the caller hardware."
    • changedInput schema / properties / explain / description
      Previous value: -"Include per-model rationale text (default true)"New value: +"Include per-entry fni_summary (factual FNI factor/spec facts) and caveats in the response (default true)"
    • changedInput schema / properties / limit / description
      Previous value: -"Max recommendations (1-20, default 5)"New value: +"Max entries returned (1-20, default 5)"
  2. Changed12 schema fields changed
    • addedInput schema / properties / constraints / description
      Added value: +"Hardware and license filters (all optional)"
    • addedInput schema / properties / constraints / properties / can_run_local / description
      Added value: +"Only models that can run locally"
    • addedInput schema / properties / constraints / properties / hosted_on / description
      Added value: +"Hosting platform filter (e.g. \"hf-inference\")"
    • addedInput schema / properties / constraints / properties / license / description
      Added value: +"Specific license (e.g. \"Apache-2.0\", \"MIT\")"
    • addedInput schema / properties / constraints / properties / license_type / description
      Added value: +"License category filter"
    • addedInput schema / properties / constraints / properties / max_params_b / description
      Added value: +"Maximum model parameters in billions"
    • addedInput schema / properties / constraints / properties / max_vram_gb / description
      Added value: +"Maximum GPU VRAM in GB (e.g. 8, 24)"
    • addedInput schema / properties / constraints / properties / min_context_length / description
      Added value: +"Minimum context window in tokens"
    • addedInput schema / properties / constraints / properties / ollama_compatible / description
      Added value: +"Only models runnable via Ollama"
    • addedInput schema / properties / explain / description
      Added value: +"Include per-model rationale text (default true)"
    • addedInput schema / properties / limit / description
      Added value: +"Max recommendations (1-20, default 5)"
    • changedInput schema / properties / task / description
      Previous value: -"Task name or description (e.g. \"text-generation\", \"code assistant\")"New value: +"Task name or natural language description (e.g. \"text-generation\", \"code assistant\", \"image classification\")"
  3. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Discloses read-only, no side effects, FNI-ranked non-paid, no billing. Acknowledges heuristic/metadata filtering limitations ('does not verify actual compatibility'). No annotations provided, so description carries full burden. Minor omission: no mention of pagination or error behavior, but constraints are well-covered.

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?

Description is front-loaded with purpose and usage, followed by limitations and alternatives. Only three sentences with no filler. Could slightly reduce redundancy (e.g., repeated 'heuristic'), but overall efficient.

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?

Given full schema coverage (4 params, 1 required) and no output schema, description covers tool behavior, result ranking, and parameter explanation. Could benefit from brief mention of return structure (e.g., array of model entries), but the 'explain' parameter hints at per-entry summaries. Adequate for complexity.

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. Description adds value by explaining that constraints are metadata/heuristic filters, not verified runtime checks. Also notes that results are FNI-ranked and includes explanation parameter. Slightly above baseline due to clarifying context beyond 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?

Description clearly states the tool filters catalog by metadata/constraints and returns FNI-ranked candidates. It distinguishes from siblings: unconstrained search (free2aitools_search) and keyword ranking (free2aitools_rank). Specific verb 'filter' and resource 'Free2AITools catalog.'

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?

Explicitly states 'USE WHEN you have concrete constraints' and provides clear exclusions: not for inference, not a decision tool, not verified compatibility. Names alternative tools for different use cases. Complete guidance.

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

All Free2AITools 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