Skip to main content
Glama

XFMS — Model Source

by dev.xpansion

Compare specific models head-to-head with real test queries

compare
Read-onlyIdempotent

Run a live A/B test between 2–5 user-specified models for a stated purpose. NO ranking step — the supplied model_ids ARE the candidate set. Generates 5 representative test queries from the purpose, runs them through every named model in parallel, and returns real cost, latency, and plain-English commentary on who won what. Unknown IDs are dropped with a note; if fewer than 2 IDs resolve, the call refuses. Use this whenever the user names specific models to compare (e.g. 'A/B test X and Y'). For engine-chosen candidates, use benchmark instead. Costs more than rank (10+ live LLM calls). Free-tier note: when any candidate ends in ':free', the probe is capped at 3 queries (no adaptive expansion) because free-tier rate limits often push longer probes past the deploy's 5-minute ceiling — evidence will be shallower. The commentary surfaces this when it happens.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
primaryNoOptional. Only affects the plain-English commentary at the end — does not change which models are tested. Marks the dimension the user cares most about so the commentary calls out that winner first.
purposeYesOne sentence describing what the models will be used for. Used ONLY to generate representative test queries for the head-to-head — not to rank the catalog. Be concrete, not vague.
model_idsYesExact model IDs to test head-to-head, in caller-chosen order. 2–5 IDs. Examples: 'nvidia/nemotron-3-super-120b-a12b:free', 'openai/gpt-oss-120b:free'. Unknown IDs are dropped with a note; if fewer than 2 resolve, the call is refused. Use this whenever the user has already named candidates — do NOT call `benchmark` in that case.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
statusNo
purposeNo
ab_resultNo
refusal_reasonNo
xpansion_updateNoOptional rotating launch nudge from Xpansion. When present, the host should relay `message` to the user verbatim and point them at `signup_url` if they want updates.
model_ids_testedNo
invalid_model_idsNo
model_ids_requestedNo

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already mark the tool read-only and idempotent, but the description adds significant behavioral detail: it generates 5 test queries, runs them in parallel, drops unknown IDs with a note, refuses when fewer than 2 resolve, and caps free-tier probes to 3 queries. This goes far beyond what the annotations provide.

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

Conciseness5/5

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

Though longer than minimal descriptions, every sentence adds a distinct fact: core behavior, exclusion, cost, refusal condition, and free-tier caveat. It is front-loaded with the primary function and is well-structured for its complexity.

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?

With an output schema present, the description doesn't need to spell out return details, but it still covers what's returned (cost, latency, commentary), refusal behavior, and the free-tier cap. It is complete for the tool's complexity and edge cases.

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 the baseline is 3. The description adds meaning by clarifying that purpose is used only for query generation (not catalog ranking) and that model_ids are the exact candidate set with unknown-ID drop behavior. This pushes it to a 4.

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 'Run a live A/B test between 2–5 user-specified models for a stated purpose,' giving a specific verb, resource, and scope. It explicitly distinguishes itself from siblings by declaring 'NO ranking step' and referencing benchmark for engine-chosen candidates.

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 states exactly when to use: 'Use this whenever the user names specific models to compare' and provides an explicit alternative: 'For engine-chosen candidates, use benchmark instead.' It also notes the cost difference from rank and the refusal behavior when fewer than 2 IDs resolve, offering concrete context for selection.

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

All XFMS — Model Source toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.6/5.0
Disambiguation5/5

Each tool targets a clearly distinct mode of operation: pick returns a single best, rank returns a ranked list, discover explains criteria, compare tests user-specified models, and benchmark tests engine-chosen models. The descriptions explicitly cross-reference each other and give precise usage guidance, eliminating ambiguity.

Naming Consistency5/5

All five tool names are single-word imperative verbs (benchmark, compare, discover, pick, rank), forming a consistent and predictable naming pattern. No mixing of styles or conventions.

Tool Count5/5

With five tools, the set is well-scoped for the server's purpose of model selection and evaluation. Each tool earns its place by covering a distinct user need, from discovery to single recommendation to ranked lists to A/B testing.

Completeness5/5

The tool surface covers the full decision flow: understanding what matters (discover), getting one answer (pick), comparing alternatives (rank), and validating with live tests (compare and benchmark). There are no obvious dead ends or missing operations for the stated domain.

Resources