Skip to main content
Glama

Server Details

Will a local LLM run on your hardware? GGUF quant, buy-vs-rent-vs-API cost, used-GPU prices.

Status
Healthy
Last Tested
Transport
Streamable HTTP
URL

Glama MCP Gateway

Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.

MCP client
Glama
MCP server

Full call logging

Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.

Tool access control

Enable or disable individual tools per connector, so you decide what your agents can and cannot do.

Managed credentials

Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.

Usage analytics

See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.

100% free. Your data is private.
Tool DescriptionsA

Average 3.8/5 across 9 of 9 tools scored. Lowest: 3.2/5.

Server CoherenceA
Disambiguation4/5

Tools have mostly distinct purposes, though there is some overlap between cheapest_hardware_for_model and recommend_hardware, which both suggest machines for a model. Can_i_run_it also partially overlaps with these. However, descriptions clearly differentiate them.

Naming Consistency3/5

Most tools follow verb_noun pattern (list_hardware, compare_hardware), but can_i_run_it is a question and cost_compare is noun_verb, creating minor inconsistency.

Tool Count5/5

9 tools is well-scoped for a domain of hardware/model comparison, covering all key actions without being excessive.

Completeness4/5

Covers main workflows: compatibility check, cost analysis, recommendations, and listings. Lacks advanced filtering or detailed hardware specs, but core functionality is present.

Available Tools

9 tools
can_i_run_itCan I run it?AInspect

Will a given local LLM run on given hardware? Returns fit, the best quant that fits, theoretical tok/s, and real owner-measured tok/s where available.

ParametersJSON Schema
NameRequiredDescriptionDefault
modelNoModel name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names.
mxfp4NoTrue if the model ships natively in MXFP4 (e.g. gpt-oss)
contextNoContext window in tokens (default 8192)
total_bNoFor an unlisted model: total parameters in billions
unifiedNoTrue for unified-memory machines (Macs, Strix Halo, CPU+RAM)
vram_gbNoFor custom hardware: VRAM or unified memory in GB
active_bNoFor an unlisted model: active params in billions (= total for dense, less for MoE)
hardwareNoHardware name/id, e.g. 'rtx-3090', 'Mac 128GB', 'Strix Halo'. Use list_hardware to see known ones.
kv_precisionNoKV cache precision (default f16)
bandwidth_gbpsNoFor custom hardware: memory bandwidth in GB/s
Behavior3/5

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

No annotations are provided, so the description must carry the full burden. It explains the return values (fit, quant, tok/s) but does not disclose if it is read-only, requires internet, or caches results.

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?

The description is a single, well-structured sentence that front-loads the purpose and key outputs. No wasted words.

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?

Given 10 parameters and no output schema, the description adequately covers the purpose and outputs but lacks details on output structure (e.g., is it a single object or array?) and error handling.

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

Parameters3/5

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

Schema coverage is 100% and parameter descriptions are already clear. The description adds context about what the tool returns but does not enhance understanding of individual parameters beyond 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 description clearly states it checks if a given local LLM runs on hardware and returns detailed performance info. It distinguishes from sibling tools like list_models and recommend_hardware by focusing on compatibility and speed estimates.

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

Usage Guidelines3/5

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

The description implies usage for checking model-hardware compatibility, but does not explicitly state when to use this tool versus alternatives like recommend_hardware or cheap_hardware. No when-not or alternative tool mentions.

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

cheapest_hardware_for_modelCheapest hardware for a modelAInspect

The cheapest catalogued, buyable machine that runs a given model at Q4 with the requested context.

ParametersJSON Schema
NameRequiredDescriptionDefault
modelNoModel name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names.
mxfp4NoTrue if the model ships natively in MXFP4 (e.g. gpt-oss)
contextNoContext window in tokens (default 8192)
total_bNoFor an unlisted model: total parameters in billions
active_bNoFor an unlisted model: active params in billions (= total for dense, less for MoE)
Behavior3/5

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

With no annotations, the description carries full burden. It mentions Q4 quantization and catalogued buyable machines but does not disclose fallback behavior for unlisted models, default context handling, or absence of hardware matches.

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?

The description is a single sentence that efficiently conveys the core purpose without extraneous words. It is appropriately front-loaded.

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?

Given five parameters, no output schema, and no annotations, the description is minimal. It lacks information about return format, error handling, or default values, but it covers the essential purpose for a specialized tool.

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

Parameters3/5

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 adds context about Q4 and buyable machines but does not further explain parameters like total_b or active_b beyond what the schema provides.

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 clearly states the tool finds the cheapest catalogued, buyable machine for a given model at Q4 quantization and requested context. The name reinforces this, and it distinguishes from siblings like 'can_i_run_it' and 'compare_hardware'.

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

Usage Guidelines3/5

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

The description implies usage for finding cheapest hardware for a specific model, but it does not provide explicit guidance on when to use this tool versus alternatives like 'recommend_hardware' or 'can_i_run_it'. No when-not-to-use or alternative suggestions are given.

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

compare_hardwareCompare hardwareAInspect

Side-by-side memory, bandwidth, price, and (with a model) fit + tok/s for 2 to 4 machines.

ParametersJSON Schema
NameRequiredDescriptionDefault
modelNoModel name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names.
mxfp4NoTrue if the model ships natively in MXFP4 (e.g. gpt-oss)
contextNoContext window in tokens (default 8192)
total_bNoFor an unlisted model: total parameters in billions
active_bNoFor an unlisted model: active params in billions (= total for dense, less for MoE)
hardwareYes2 to 4 hardware names/ids, comma-separated
kv_precisionNoKV cache precision (default f16)
Behavior3/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It explains what is compared (memory, bandwidth, price, etc.) and that adding a model includes fit and tok/s. However, it does not mention whether the tool is read-only, requires authentication, or has any side effects.

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?

The description is a single, well-structured sentence that efficiently conveys the tool's purpose and key features with no unnecessary words.

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?

The description is fairly complete for a comparison tool given the schema covers all parameters. It does not explain the structure of the output (no output schema), but the listed comparison dimensions (memory, bandwidth, price) give a reasonable expectation of the result.

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 100%, so parameters are already well-documented. The description adds value by explaining that the hardware parameter accepts 2-4 machine names and that model inclusion adds fit and tokens/s, providing context beyond 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 description clearly states the tool's purpose: side-by-side comparison of memory, bandwidth, price, and optionally model fit and tokens per second for 2 to 4 machines. It distinguishes from sibling tools like can_i_run_it or cheapest_hardware_for_model by focusing on multi-machine comparison.

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?

The description specifies the tool is for comparing 2 to 4 machines, implicitly guiding when to use it. It does not explicitly state when not to use it or mention alternatives, but the sibling list provides context for alternative tools.

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

cost_compareCost: buy vs rent vs APIAInspect

Buy vs rent vs API cost to run a model locally: monthly/1y/3y totals, break-even months, and the energy cost per 1M tokens. Same math as /cost-calculator/.

ParametersJSON Schema
NameRequiredDescriptionDefault
apiNoAPI $/million tokens (default 1.0)
kwhNoElectricity $/kWh (default 0.16)
rentNoCloud GPU $/hour (default 0.59)
hoursNoActive hours per day (default 3)
tdp_wNoFor custom hardware: board power draw in watts
tokensNoTokens generated per day, for the API comparison (default 300000)
hardwareNoCatalogued hardware name/id (see list_hardware), e.g. 'rtx-3090-used'
price_usdNoFor custom hardware: price in USD
Behavior3/5

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

With no annotations provided, the description carries the sole burden of behavioral disclosure. It states it calculates totals, break-even, and energy cost, but does not disclose whether it requires external data, is read-only, or has any side effects. The description is sufficient but lacks depth on potential limitations or requirements.

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?

The description is two sentences long, front-loads the main purpose, and contains no superfluous information. Every word contributes to understanding, earning a top score.

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?

Given the lack of an output schema, the description provides a conceptual outline of return values (monthly/1y/3y totals, break-even months, energy cost) but does not specify the exact format or structure of the response, leaving some ambiguity for an AI agent.

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

Parameters3/5

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

Input schema has 100% parameter description coverage, so the description adds no additional meaning beyond the schema. The baseline of 3 is appropriate; the description does not elaborate on parameter relationships or usage nuances.

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 explicitly states the tool's purpose: comparing buy, rent, and API costs for running a model locally. It lists specific outputs (monthly/1y/3y totals, break-even months, energy cost per 1M tokens), which clearly distinguishes it from sibling tools like 'list_hardware' or 'recommend_hardware' that focus on hardware selection rather than cost comparison.

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?

The description implies usage for cost analysis without explicit guidance. It mentions 'Same math as /cost-calculator/' but does not specify when to use this tool over alternatives like 'cheapest_hardware_for_model'. Still, the context is clear enough for an agent to infer appropriate use cases for cost comparison.

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

get_used_gpu_pricesUsed GPU pricesAInspect

Current typical used-GPU prices for local-AI rigs (eBay Browse API median asking + hand-verified, monthly).

ParametersJSON Schema
NameRequiredDescriptionDefault
gpuNoOptional name/id filter, e.g. "3090"
Behavior2/5

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

With no annotations, the description must disclose behavioral traits. It only states the data source and update frequency, but omits details like authentication requirements, rate limits, error handling, or what happens when no prices are found.

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?

The description is a single, concise sentence that front-loads the key purpose and source detail. Every word serves a purpose, with no redundancy.

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 simple tool with one optional parameter and no output schema, the description covers the data source, scope, and update frequency. It could briefly mention the output format (e.g., JSON with prices), but overall it provides sufficient context for an agent.

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

Parameters3/5

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

The sole parameter 'gpu' is already described in the schema as an optional filter with an example. The description adds no additional meaning beyond that. Schema coverage is 100%, so a baseline of 3 is appropriate.

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 it returns 'typical used-GPU prices for local-AI rigs' derived from specific data sources (eBay Browse API median, hand-verified, monthly). This identifies the exact resource and scope, distinguishing it from sibling tools like 'list_hardware' or 'cost_compare'.

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

Usage Guidelines3/5

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

The description implies use for obtaining price data, but provides no explicit guidance on when to use this tool versus alternatives (e.g., 'cost_compare' or 'recommend_hardware'). No exclusions or prerequisites are mentioned.

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

list_hardwareList hardwareAInspect

List the machines the tools know about (memory, bandwidth, price, buy link).

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Behavior3/5

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

No annotations provided, so description carries the burden. It indicates a safe read-only listing operation (listing with no side effects). However, it does not mention data freshness, error conditions, or confirm it is non-destructive.

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?

One sentence that communicates the core purpose and included fields. No wasted words; highly efficient for a simple list tool.

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 parameter-less tool with no output schema, the description adequately lists the returned fields. However, it does not clarify the scope (e.g., all known hardware vs. hardware for models) or mention sorting/pagination.

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?

There are 0 parameters, so baseline is 4. The description adds no parameter info because none exist.

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 explicitly states it lists machines with memory, bandwidth, price, and buy link. It distinguishes from siblings like 'cheapest_hardware_for_model' or 'compare_hardware' which are focused on specific comparisons or cost optimization.

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

Usage Guidelines3/5

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

Usage is implied: use this to see all known machines. No explicit guidance on when not to use or alternatives. Sibling names suggest more specific tools exist, but the description does not direct the agent to them.

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

list_modelsList modelsAInspect

List the local LLM model classes the tools know about (params, dense/MoE, native context).

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Behavior3/5

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

No annotations are provided, so the description must fully disclose behavior. It states the tool lists models but does not mention any side effects, access requirements, or response format. Adequate for a simple read operation but incomplete.

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?

The description is a single, front-loaded sentence that efficiently conveys the tool's purpose without unnecessary words. Every phrase earns its place.

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 no output schema and zero parameters, the description adequately explains the return value (list of model classes with attributes). It could mention the format (e.g., array of objects) but is largely complete.

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?

The tool has no parameters, so schema coverage is 100% by default. The description adds value by specifying what information is included in the list, going beyond the empty 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 description clearly specifies the tool lists local LLM model classes and includes key attributes (params, dense/MoE, native context). It distinctly sets itself apart from sibling tools which focus on hardware or cost.

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

Usage Guidelines3/5

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

The description does not provide explicit guidance on when to use this tool versus alternatives like can_i_run_it or list_hardware. Usage is implicit (for listing models) but lacks when-not-to-use details.

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

recommend_hardwareRecommend hardwareBInspect

Ranked list of catalogued, buyable machines that run a model at the requested context, cheapest first, with an optional budget cap.

ParametersJSON Schema
NameRequiredDescriptionDefault
modelNoModel name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names.
mxfp4NoTrue if the model ships natively in MXFP4 (e.g. gpt-oss)
budgetNoOptional max price in USD
contextNoContext window in tokens (default 8192)
total_bNoFor an unlisted model: total parameters in billions
active_bNoFor an unlisted model: active params in billions (= total for dense, less for MoE)
kv_precisionNoKV cache precision (default f16)
Behavior3/5

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

No annotations are provided, so the description carries full burden. It discloses that the tool returns a 'ranked list' sorted by price, which is helpful. However, it does not explain whether the operation is read-only, how 'buyable' is determined, or any potential side effects like query costs or data freshness. This is minimally adequate but lacks depth.

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?

The description is a single sentence that efficiently conveys the core purpose: a ranked list, criteria, and optional budget. It is well-structured and front-loaded with the key output ('Ranked list'). No unnecessary words.

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

Completeness2/5

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

Given the tool has 7 parameters and no output schema, the description does not cover important details: how to combine 'model' with 'total_b'/'active_b', what 'catalogued' means, or the return format (besides being a list). It leaves significant gaps for an agent to use the tool correctly.

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

Parameters3/5

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

Schema description coverage is 100%, so all parameters are documented in the schema. The description adds only a mention of 'model,' 'context,' and 'budget cap,' which is already covered. It does not explain the relationship between 'model' and 'total_b'/'active_b' for unlisted models, so it provides no added value beyond the schema.

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

Purpose4/5

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

The description clearly states the tool returns a ranked list of machines for a given model and context, with optional budget cap. It specifies 'catalogued, buyable machines' and 'cheapest first,' which distinguishes it from siblings like 'cheapest_hardware_for_model' that likely return a single result. However, it does not explicitly differentiate from all siblings, so a 4 is appropriate.

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?

The description provides no guidance on when to use this tool versus alternatives such as 'cheapest_hardware_for_model' or 'can_i_run_it.' It implies usage for ranked hardware recommendations but does not state when to avoid it or mention prerequisites like listing models first.

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

recommend_quantRecommend a quantAInspect

Which GGUF quantization to download for a model on given hardware: the full quant ladder with file size, max context, and tok/s for each, plus the recommended pick.

ParametersJSON Schema
NameRequiredDescriptionDefault
modelNoModel name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names.
mxfp4NoTrue if the model ships natively in MXFP4 (e.g. gpt-oss)
contextNoContext window in tokens (default 8192)
total_bNoFor an unlisted model: total parameters in billions
unifiedNoTrue for unified-memory machines (Macs, Strix Halo, CPU+RAM)
vram_gbNoFor custom hardware: VRAM or unified memory in GB
active_bNoFor an unlisted model: active params in billions (= total for dense, less for MoE)
hardwareNoHardware name/id, e.g. 'rtx-3090', 'Mac 128GB', 'Strix Halo'. Use list_hardware to see known ones.
kv_precisionNoKV cache precision (default f16)
bandwidth_gbpsNoFor custom hardware: memory bandwidth in GB/s
Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses what the tool outputs (quant ladder with file size, max context, tok/s, recommended pick), but does not describe any side effects, data sources, or limitations. The behavioral traits are reasonably clear for a recommendation tool.

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?

The description is a single, efficient sentence that front-loads the key purpose and output. Every word earns its place without redundancy.

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 10 parameters with full schema coverage and no output schema, the description is complete enough. It explains the output format. However, it could provide more context on how the recommendation is determined (e.g., model accuracy vs speed trade-offs).

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

Parameters3/5

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

Schema description coverage is 100%, so the input schema already documents all parameters well. The tool description adds no additional meaning beyond stating the overall purpose. Baseline of 3 is appropriate since the schema covers the parameters.

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 clearly states the tool's purpose: recommending a GGUF quantization for a model on given hardware, and specifies the output includes the quant ladder with file size, max context, tok/s, and a recommended pick. It distinguishes from siblings like 'recommend_hardware' which recommend hardware.

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

Usage Guidelines3/5

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

The description implies usage context (when you need to choose a quantization for a model on hardware), but does not explicitly state when to use this tool versus alternatives like 'can_i_run_it' or 'list_models'. No when-not or exclusions are provided.

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

Discussions

No comments yet. Be the first to start the discussion!

Try in Browser

Your Connectors

Sign in to create a connector for this server.

Resources