Skip to main content
Glama

Match a workload to the cheapest GPU

match_workload
Read-onlyIdempotent

Ranks up to eight GPU configurations that can run a job at the lowest live price. Describe the job in query (an open-weight model to serve or fine-tune, a model size, or a GPU need) or with the structured fields. Each match gives the GPU count, the USD per hour for the whole configuration and a one-line reason; the answer also states the VRAM the job needs and how much cheaper the top match is than a hyperscaler running the same job. Use it to decide where to run a workload; use list_gpu_prices for the price of a named GPU. Open-weight models only: an API-only model such as GPT-4 returns no matches and a note. Ranked on price and fit alone: no provider pays for placement (each match still reports partner, a provider that pays FastGPU a referral). Hard limits (budget_usd_hr, max_total_usd with duration_hours, max_quote_age_minutes) drop every configuration that breaks them; limits reports what was dropped. Read-only: it does not rent, reserve or launch GPUs. No key required.

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": "match_workload"
  }
}

Input Schema

NameRequiredDescriptionDefault
spotNoSet true to include interruptible spot capacity for a cheaper rate.
taskNoWhat the job does.
modelNoOpen model name to size against, e.g. "Llama 3 70B", "Qwen 72B", "Mixtral".
queryNoPlain-language job, e.g. "cheapest to serve Llama 3 70B", "2x H100 for fine-tuning" or "a GPU with 80GB of memory". Provide this OR a structured spec below.
regionNoRestrict to a data-residency region.
vram_gbNoRough VRAM the job needs, in GB, if you already know it.
params_bNoModel size in billions of parameters when no exact model is named.
reservedNoSet true to include reserved / committed-term capacity for a lower rate.
gpu_countNoExact positive GPU count. Overrides a count in query text. Returns no matches if no supported configuration fits; omit for automatic sizing.
precisionNoNumeric precision to size the model at.
weights_gbNoMeasured size of the weights as stored, in GB: the file you will load (for example a GGUF Q4_K_M build, which holds more bits per parameter than its nominal 4). Replaces parameters times bytes per parameter in the memory estimate. Used for a model sized by its parameter count; the answer's workload.weights_gb is null when it was not (an image or speech model sized as a whole pipeline).
concurrencyNoFor a serving or fine-tuning job: requests (or sequences) processed at once, 1 to 2048 (default 1). Sizes the KV cache, and for serving the tokens_per_sec and usd_per_million_tokens estimate: more requests at once share each step's weight reads.
budget_usd_hrNoHard limit on the hourly price of the whole configuration, in USD. Configurations above it are not returned.
max_total_usdNoHard limit on estimated_total_usd, the GPU rental cost of the whole job, in USD. Needs duration_hours. Configurations above it are not returned.
context_tokensNoTokens of context each request holds, prompt and output together, 512 to 1000000 (default 4096). Sizes the KV cache and the per-token estimate.
duration_hoursNoHow long the job will run, in hours (fractions are fine). When sent, each match carries billed_hours and estimated_total_usd.
active_params_bNoFor a mixture-of-experts model: the parameters it runs per generated token, in billions (Qwen3-30B-A3B runs about 3). Used for tokens_per_sec and usd_per_million_tokens; the memory estimate still holds every expert. Omit it to use FastGPU's figure for a model it knows, or what the Hugging Face repo's own config.json states (workload.active_params_source says which).
engram_placementNoFor a model with Engram memory tables (DeepSeek-V4.1): gpu (default) holds them in GPU memory; host keeps them in the machine's RAM, as SGLang's --engram-config '{"placement":"cpu"}' does, so vram_required_gb leaves them out and workload.engram_gb is the RAM the machine needs for them. A token reads only a few of their rows, so the per-token estimate is the same either way.
min_gpu_memory_gbNoMemory each GPU card must have, in GB (e.g. 80 for 80GB-class cards such as the H100 or A100 80GB). Smaller cards are never returned. On its own it lists every card that size, cheapest first.
max_quote_age_minutesNoHard limit on how old a price quote may be, in minutes. Configurations whose price was fetched from the provider longer ago are not returned.

Output Schema

NameRequiredDescriptionDefault
heroNo
noteNoWhy there are no matches, when there are none.
as_ofNoWhen this answer was computed (ISO 8601). Quote ages are measured against it.
countYes
errorNoPresent when the request was not valid; says what to send instead.
staleNo
limitsNoThe hard limits this answer applied (null when one was not sent) and how many configurations each one left out.
matchesYes
workloadNo
updated_atNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed15 schema fields changed
    • addedInput schema / properties / active_params_b
      Added value: +{
      +  "description": "For a mixture-of-experts model: the parameters it runs per generated token, in billions (Qwen3-30B-A3B runs about 3). Used for tokens_per_sec and usd_per_million_tokens; the memory estimate still holds every expert. Omit it to use FastGPU's figure for a model it knows, or what the Hugging Face repo's own config.json states (workload.active_params_source says which).",
      +  "type": "number"
      +}
    • addedInput schema / properties / concurrency
      Added value: +{
      +  "description": "For a serving or fine-tuning job: requests (or sequences) processed at once, 1 to 2048 (default 1). Sizes the KV cache, and for serving the tokens_per_sec and usd_per_million_tokens estimate: more requests at once share each step's weight reads.",
      +  "type": "integer"
      +}
    • addedInput schema / properties / context_tokens
      Added value: +{
      +  "description": "Tokens of context each request holds, prompt and output together, 512 to 1000000 (default 4096). Sizes the KV cache and the per-token estimate.",
      +  "type": "integer"
      +}
    • addedInput schema / properties / engram_placement
      Added value: +{
      +  "description": "For a model with Engram memory tables (DeepSeek-V4.1): gpu (default) holds them in GPU memory; host keeps them in the machine's RAM, as SGLang's --engram-config '{\"placement\":\"cpu\"}' does, so vram_required_gb leaves them out and workload.engram_gb is the RAM the machine needs for them. A token reads only a few of their rows, so the per-token estimate is the same either way.",
      +  "enum": [
      +    "gpu",
      +    "host"
      +  ],
      +  "type": "string"
      +}
    • addedOutput schema / properties / limits / properties / nearest_excluded / properties / token_model
      Added value: +{
      +  "description": "The working behind tokens_per_sec (serving only), a model and not a measurement: each decode step reads streamed_params_b x bytes_per_param of weights (weights_gb_per_step) plus every request's KV cache (kv_gb_per_step); tokens_per_sec is the lowest of memory_tokens_per_sec = requests x cards_counted x card_bandwidth_gbs x memory_efficiency / (weights_gb_per_step + kv_gb_per_step), the compute ceiling compute_tokens_per_sec, and latency_tokens_per_sec = requests / min_step_ms (no decode step is credited faster than the fastest published single-request decode). A best case: real serving stacks usually reach less.",
      +  "properties": {
      +    "bound": {
      +      "enum": [
      +        "memory",
      +        "compute",
      +        "latency"
      +      ],
      +      "type": "string"
      +    },
      +    "bytes_per_param": {
      +      "type": "number"
      +    },
      +    "card_bandwidth_gbs": {
      +      "type": "number"
      +    },
      +    "cards_counted": {
      +      "type": "integer"
      +    },
      +    "compute_tokens_per_sec": {
      +      "type": "number"
      +    },
      +    "kv_gb_per_step": {
      +      "type": "number"
      +    },
      +    "latency_tokens_per_sec": {
      +      "type": "number"
      +    },
      +    "memory_efficiency": {
      +      "type": "number"
      +    },
      +    "memory_tokens_per_sec": {
      +      "type": "number"
      +    },
      +    "min_step_ms": {
      +      "type": "number"
      +    },
      +    "requests": {
      +      "type": "integer"
      +    },
      +    "streamed_params_b": {
      +      "type": "number"
      +    },
      +    "weights_gb_per_step": {
      +      "type": "number"
      +    }
      +  },
      +  "type": [
      +    "object",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / matches / items / properties / token_model
      Added value: +{
      +  "description": "The working behind tokens_per_sec (serving only), a model and not a measurement: each decode step reads streamed_params_b x bytes_per_param of weights (weights_gb_per_step) plus every request's KV cache (kv_gb_per_step); tokens_per_sec is the lowest of memory_tokens_per_sec = requests x cards_counted x card_bandwidth_gbs x memory_efficiency / (weights_gb_per_step + kv_gb_per_step), the compute ceiling compute_tokens_per_sec, and latency_tokens_per_sec = requests / min_step_ms (no decode step is credited faster than the fastest published single-request decode). A best case: real serving stacks usually reach less.",
      +  "properties": {
      +    "bound": {
      +      "enum": [
      +        "memory",
      +        "compute",
      +        "latency"
      +      ],
      +      "type": "string"
      +    },
      +    "bytes_per_param": {
      +      "type": "number"
      +    },
      +    "card_bandwidth_gbs": {
      +      "type": "number"
      +    },
      +    "cards_counted": {
      +      "type": "integer"
      +    },
      +    "compute_tokens_per_sec": {
      +      "type": "number"
      +    },
      +    "kv_gb_per_step": {
      +      "type": "number"
      +    },
      +    "latency_tokens_per_sec": {
      +      "type": "number"
      +    },
      +    "memory_efficiency": {
      +      "type": "number"
      +    },
      +    "memory_tokens_per_sec": {
      +      "type": "number"
      +    },
      +    "min_step_ms": {
      +      "type": "number"
      +    },
      +    "requests": {
      +      "type": "integer"
      +    },
      +    "streamed_params_b": {
      +      "type": "number"
      +    },
      +    "weights_gb_per_step": {
      +      "type": "number"
      +    }
      +  },
      +  "type": [
      +    "object",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / workload / properties / active_params_b
      Added value: +{
      +  "description": "Parameters a mixture-of-experts model runs per generated token, in billions; null for a dense model.",
      +  "type": [
      +    "number",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / workload / properties / active_params_source
      Added value: +{
      +  "description": "Where active_params_b comes from: the request, FastGPU's model list, the repo's name, or the repo's config.json.",
      +  "enum": [
      +    "stated",
      +    "registry",
      +    "name",
      +    "config",
      +    null
      +  ],
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / workload / properties / concurrency
      Added value: +{
      +  "description": "Requests the job is sized for at once.",
      +  "type": "integer"
      +}
    • addedOutput schema / properties / workload / properties / context_tokens
      Added value: +{
      +  "description": "Context each request holds, in tokens.",
      +  "type": "integer"
      +}
    • addedOutput schema / properties / workload / properties / engram_gb
      Added value: +{
      +  "description": "The Engram tables' size at this sizing, in GB: in vram_required_gb when engram_placement is gpu, the host RAM they need when it is host.",
      +  "type": [
      +    "number",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / workload / properties / engram_params_b
      Added value: +{
      +  "description": "Parameters held in Engram lookup tables, in billions (DeepSeek-V4.1); null when the model has none.",
      +  "type": [
      +    "number",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / workload / properties / engram_placement
      Added value: +{
      +  "enum": [
      +    "gpu",
      +    "host",
      +    null
      +  ],
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / workload / properties / experts
      Added value: +{
      +  "type": [
      +    "integer",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / workload / properties / experts_active
      Added value: +{
      +  "type": [
      +    "integer",
      +    "null"
      +  ]
      +}
  2. Changed2 schema fields changed
    • addedOutput schema / properties / limits / properties / nearest_excluded / properties / rent_url
      Added value: +{
      +  "description": "Opens this offer on the provider's own site, through a FastGPU redirect that counts the click. When partner is true the link carries FastGPU's referral code (the provider pays FastGPU a referral; the price is the same). Give it to the user only after they choose this offer.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / matches / items / properties / rent_url
      Added value: +{
      +  "description": "Opens this offer on the provider's own site, through a FastGPU redirect that counts the click. When partner is true the link carries FastGPU's referral code (the provider pays FastGPU a referral; the price is the same). Give it to the user only after they choose this offer.",
      +  "type": "string"
      +}
  3. Changed1 schema field changed
    • addedInput schema / properties / weights_gb
      Added value: +{
      +  "description": "Measured size of the weights as stored, in GB: the file you will load (for example a GGUF Q4_K_M build, which holds more bits per parameter than its nominal 4). Replaces parameters times bytes per parameter in the memory estimate. Used for a model sized by its parameter count; the answer's workload.weights_gb is null when it was not (an image or speech model sized as a whole pipeline).",
      +  "type": "number"
      +}
  4. Changed14 schema fields changed
    • changedInput schema / properties / budget_usd_hr / description
      Previous value: -"Only recommend configs at or under this hourly budget."New value: +"Hard limit on the hourly price of the whole configuration, in USD. Configurations above it are not returned."
    • addedInput schema / properties / duration_hours
      Added value: +{
      +  "description": "How long the job will run, in hours (fractions are fine). When sent, each match carries billed_hours and estimated_total_usd.",
      +  "type": "number"
      +}
    • addedInput schema / properties / max_quote_age_minutes
      Added value: +{
      +  "description": "Hard limit on how old a price quote may be, in minutes. Configurations whose price was fetched from the provider longer ago are not returned.",
      +  "type": "number"
      +}
    • addedInput schema / properties / max_total_usd
      Added value: +{
      +  "description": "Hard limit on estimated_total_usd, the GPU rental cost of the whole job, in USD. Needs duration_hours. Configurations above it are not returned.",
      +  "type": "number"
      +}
    • addedOutput schema / properties / as_of
      Added value: +{
      +  "description": "When this answer was computed (ISO 8601). Quote ages are measured against it.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / error
      Added value: +{
      +  "description": "Present when the request was not valid; says what to send instead.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / limits
      Added value: +{
      +  "description": "The hard limits this answer applied (null when one was not sent) and how many configurations each one left out.",
      +  "properties": {
      +    "budget_usd_hr": {
      +      "type": [
      +        "number",
      +        "null"
      +      ]
      +    },
      +    "duration_hours": {
      +      "type": [
      +        "number",
      +        "null"
      +      ]
      +    },
      +    "excluded": {
      +      "properties": {
      +        "older_than_max_quote_age_minutes": {
      +          "type": "integer"
      +        },
      +        "over_budget_usd_hr": {
      +          "type": "integer"
      +        },
      +        "over_max_total_usd": {
      +          "type": "integer"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "max_quote_age_minutes": {
      +      "type": [
      +        "number",
      +        "null"
      +      ]
      +    },
      +    "max_total_usd": {
      +      "type": [
      +        "number",
      +        "null"
      +      ]
      +    },
      +    "nearest_excluded": {
      +      "description": "When the limits leave no match: the cheapest configuration that can still run the job, and the limits it breaks.",
      +      "properties": {
      +        "billed_hours": {
      +          "description": "Hours the provider bills for duration_hours: rounded up to whole hours on a per-hour meter and to whole minutes on a per-minute meter. Null when duration_hours was not sent.",
      +          "type": [
      +            "number",
      +            "null"
      +          ]
      +        },
      +        "billing_increment": {
      +          "description": "How this provider's meter ticks for on-demand rental; varies means FastGPU has no verified figure.",
      +          "enum": [
      +            "per-second",
      +            "per-minute",
      +            "per-hour",
      +            "varies"
      +          ],
      +          "type": "string"
      +        },
      +        "breaks": {
      +          "items": {
      +            "type": "string"
      +          },
      +          "type": "array"
      +        },
      +        "effective_usd_hr": {
      +          "type": "number"
      +        },
      +        "estimated_total_usd": {
      +          "description": "effective_usd_hr times billed_hours, rounded up to the cent. GPU rental only: storage, data transfer, CPU and memory billed separately, and provider minimums are not included. Null when duration_hours was not sent.",
      +          "type": [
      +            "number",
      +            "null"
      +          ]
      +        },
      +        "fetched_at": {
      +          "description": "When this price was fetched from the provider (ISO 8601).",
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "fits_single_card": {
      +          "type": "boolean"
      +        },
      +        "gpu": {
      +          "type": "string"
      +        },
      +        "gpu_count": {
      +          "type": "integer"
      +        },
      +        "monthly_usd": {
      +          "type": "number"
      +        },
      +        "offer_type": {
      +          "type": "string"
      +        },
      +        "over_budget": {
      +          "type": "boolean"
      +        },
      +        "page_url": {
      +          "description": "Absolute URL of this GPU's live price page, with every live offer.",
      +          "type": "string"
      +        },
      +        "partner": {
      +          "type": "boolean"
      +        },
      +        "provider": {
      +          "type": "string"
      +        },
      +        "provider_label": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "quote_age_seconds": {
      +          "description": "Seconds between fetched_at and as_of. Null when the fetch time is unknown.",
      +          "type": [
      +            "integer",
      +            "null"
      +          ]
      +        },
      +        "reason": {
      +          "type": "string"
      +        },
      +        "reliability": {
      +          "type": "string"
      +        },
      +        "score": {
      +          "type": [
      +            "number",
      +            "null"
      +          ]
      +        },
      +        "tokens_per_sec": {
      +          "type": [
      +            "number",
      +            "null"
      +          ]
      +        },
      +        "url": {
      +          "description": "Site-relative path of this GPU's live price page, e.g. /gpus/h100-sxm.",
      +          "type": "string"
      +        },
      +        "usd_per_million_tokens": {
      +          "type": [
      +            "number",
      +            "null"
      +          ]
      +        }
      +      },
      +      "type": [
      +        "object",
      +        "null"
      +      ]
      +    }
      +  },
      +  "type": "object"
      +}
    • addedOutput schema / properties / matches / items / properties / billed_hours
      Added value: +{
      +  "description": "Hours the provider bills for duration_hours: rounded up to whole hours on a per-hour meter and to whole minutes on a per-minute meter. Null when duration_hours was not sent.",
      +  "type": [
      +    "number",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / matches / items / properties / billing_increment
      Added value: +{
      +  "description": "How this provider's meter ticks for on-demand rental; varies means FastGPU has no verified figure.",
      +  "enum": [
      +    "per-second",
      +    "per-minute",
      +    "per-hour",
      +    "varies"
      +  ],
      +  "type": "string"
      +}
    • addedOutput schema / properties / matches / items / properties / estimated_total_usd
      Added value: +{
      +  "description": "effective_usd_hr times billed_hours, rounded up to the cent. GPU rental only: storage, data transfer, CPU and memory billed separately, and provider minimums are not included. Null when duration_hours was not sent.",
      +  "type": [
      +    "number",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / matches / items / properties / fetched_at
      Added value: +{
      +  "description": "When this price was fetched from the provider (ISO 8601).",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / matches / items / properties / quote_age_seconds
      Added value: +{
      +  "description": "Seconds between fetched_at and as_of. Null when the fetch time is unknown.",
      +  "type": [
      +    "integer",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / note
      Added value: +{
      +  "description": "Why there are no matches, when there are none.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / workload / properties / gpu_vendors
      Added value: +{
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": [
      +    "array",
      +    "null"
      +  ]
      +}
  5. Changed3 schema fields changed
    • addedInput schema / properties / min_gpu_memory_gb
      Added value: +{
      +  "description": "Memory each GPU card must have, in GB (e.g. 80 for 80GB-class cards such as the H100 or A100 80GB). Smaller cards are never returned. On its own it lists every card that size, cheapest first.",
      +  "type": "integer"
      +}
    • changedInput schema / properties / query / description
      Previous value: -"Plain-language job, e.g. \"cheapest to serve Llama 3 70B\" or \"2x H100 for fine-tuning\". Provide this OR a structured spec below."New value: +"Plain-language job, e.g. \"cheapest to serve Llama 3 70B\", \"2x H100 for fine-tuning\" or \"a GPU with 80GB of memory\". Provide this OR a structured spec below."
    • addedOutput schema / properties / workload / properties / min_gpu_memory_gb
      Added value: +{
      +  "type": [
      +    "integer",
      +    "null"
      +  ]
      +}
  6. Changed2 schema fields changed
    • addedOutput schema / properties / matches / items / properties / page_url
      Added value: +{
      +  "description": "Absolute URL of this GPU's live price page, with every live offer.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / matches / items / properties / url / description
      Added value: +"Site-relative path of this GPU's live price page, e.g. /gpus/h100-sxm."
  7. Changed2 schema fields changed
    • changedInput schema / properties / gpu_count / description
      Previous value: -"Force a specific GPU count instead of letting the engine size it."New value: +"Exact positive GPU count. Overrides a count in query text. Returns no matches if no supported configuration fits; omit for automatic sizing."
    • addedOutput schema / properties / workload / properties / gpu_count
      Added value: +{
      +  "type": [
      +    "integer",
      +    "null"
      +  ]
      +}
  8. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Beyond the readOnly/idempotent annotations it discloses that nothing is rented, reserved or launched, that no key is needed, that ranking is not influenced by paid placement (each match still reports a referral partner), and that hard limits drop configurations with a reported "limits" explanation. The only mild redundancy is restating read-only, which annotations already cover.

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?

Front-loaded with what it does and what it returns, then alternatives, exclusions, ranking policy and safety limits in descending priority. It is long but dense, with nearly every clause carrying a constraint an agent needs; the opening phrase slightly echoes the title.

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 20-parameter tool with an output schema, the description covers the decision-relevant surface: how to express the job, what each match contains, model restrictions, hard limits, and that it is non-mutating. Return-value details are correctly left to the output schema rather than duplicated.

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 the schema already documents all 20 parameters in depth. The description adds useful framing — query versus structured spec as alternatives, and that budget_usd_hr, max_total_usd with duration_hours, and max_quote_age_minutes are hard filters whose effects appear in "limits" — but for most individual parameters it defers to the schema. Baseline 3 applies.

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 first sentence states a specific verb and resource with scope: "Ranks up to eight GPU configurations that can run a job at the lowest live price." It also names the distinguishing alternative (list_gpu_prices for a named GPU's price), so an agent can separate the two siblings without opening either schema.

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?

Explicit routing guidance: "Use it to decide where to run a workload; use list_gpu_prices for the price of a named GPU." It also states the when-not condition (API-only models such as GPT-4 return no matches and a note) and how to supply the job either as free-text query or structured fields.

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