Skip to main content
Glama

Etuki FinOps & LLM Pricing Oracle

check_context_cliff

Read-onlyIdempotent

Evaluates whether a prompt token count crosses vendor long-context surcharge thresholds (100K on Claude Haiku 5.5, 128K on GPT-4o, 200K on Gemini 2.5 Pro, or 272K on GPT-6.1 Sol) and returns the surcharge multiplier and recommended flat-context alternative. Deterministic threshold lookup against the embedded 563-entity UMCE registry requiring no API keys. Returns JSON with crosses_cliff_boolean, active_surcharge_multiplier (1.0x below cliff vs 2.0x-5.0x above cliff), and recommended_flat_context_model. Compares prompt_tokens directly against model's specific cliff boundary in the UMCE catalog. Use this tool before sending large prompts (>90K tokens) to avoid 2x-5x cliff surcharges; use compress_and_fold_context instead to shrink the prompt below the cliff.

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": "check_context_cliff"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoModel ID ('vendor/model-slug') to evaluate against context-window pricing cliffs.openai/gpt-6.1-sol
prompt_tokensNoInput prompt token count to test against vendor cliff thresholds.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / model / description
      Previous value: -"Model ID to check for context-window pricing cliffs."New value: +"Model ID ('vendor/model-slug') to evaluate against context-window pricing cliffs."
    • changedInput schema / properties / prompt_tokens / description
      Previous value: -"Input prompt token count to evaluate against cliff thresholds."New value: +"Input prompt token count to test against vendor cliff thresholds."
    • addedInput schema / properties / prompt_tokens / minimum
      Added value: +0
  2. Changed2 schema fields changed
    • changedInput schema / properties / model / description
      Previous value: -"Model ID"New value: +"Model ID to check for context-window pricing cliffs."
    • changedInput schema / properties / prompt_tokens / description
      Previous value: -"Prompt token count"New value: +"Input prompt token count to evaluate against cliff thresholds."
  3. Changed2 schema fields changed
    • addedInput schema / properties / model / description
      Added value: +"Model ID"
    • addedInput schema / properties / prompt_tokens / description
      Added value: +"Prompt token count"
  4. Changed16 schema fields changed
    • removedInput schema / properties / allow_async_batch
      Removed value: -{
      -  "default": true,
      -  "type": "boolean"
      -}
    • removedInput schema / properties / budget_gate_usd
      Removed value: -{
      -  "default": 0.06,
      -  "minimum": 0,
      -  "type": "number"
      -}
    • removedInput schema / properties / cache_hit_rate
      Removed value: -{
      -  "default": 0.4,
      -  "maximum": 1,
      -  "minimum": 0,
      -  "type": "number"
      -}
    • removedInput schema / properties / cold_start_cache_write
      Removed value: -{
      -  "default": false,
      -  "type": "boolean"
      -}
    • removedInput schema / properties / completion_tokens
      Removed value: -{
      -  "maximum": 9007199254740991,
      -  "minimum": 0,
      -  "type": "integer"
      -}
    • addedInput schema / properties / model / default
      Added value: +"openai/gpt-6.1-sol"
    • removedInput schema / properties / model / description
      Removed value: -"Model ID from list_supported_models (gpt-6-1-sol, claude-haiku-5-5, claude-sonnet-5-5, claude-opus-5-5, gpt-6-luna)"
    • removedInput schema / properties / pass_rate
      Removed value: -{
      -  "default": 0.96,
      -  "exclusiveMinimum": 0,
      -  "maximum": 1,
      -  "type": "number"
      -}
    • addedInput schema / properties / prompt_tokens / default
      Added value: +150000
    • removedInput schema / properties / prompt_tokens / maximum
      Removed value: -9007199254740991
    • removedInput schema / properties / prompt_tokens / minimum
      Removed value: -0
    • changedInput schema / properties / prompt_tokens / type
      Previous value: -"integer"New value: +"number"
    • removedInput schema / properties / request_id
      Removed value: -{
      -  "description": "Optional trace ID (1..64 alphanumeric/underscore/hyphen chars).",
      -  "maxLength": 64,
      -  "pattern": "^[a-zA-Z0-9_-]{1,64}$",
      -  "type": "string"
      -}
    • removedInput schema / properties / retry_rate
      Removed value: -{
      -  "default": 0.05,
      -  "maximum": 1,
      -  "minimum": 0,
      -  "type": "number"
      -}
    • removedInput schema / properties / routed_cache_hit_rate
      Removed value: -{
      -  "maximum": 1,
      -  "minimum": 0,
      -  "type": "number"
      -}
    • removedInput schema / required
      Removed value: -[
      -  "model",
      -  "prompt_tokens",
      -  "completion_tokens"
      -]
  5. Changed18 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / allow_async_batch
      Added value: +{
      +  "default": true,
      +  "type": "boolean"
      +}
    • addedInput schema / properties / budget_gate_usd
      Added value: +{
      +  "default": 0.06,
      +  "minimum": 0,
      +  "type": "number"
      +}
    • addedInput schema / properties / cache_hit_rate
      Added value: +{
      +  "default": 0.4,
      +  "maximum": 1,
      +  "minimum": 0,
      +  "type": "number"
      +}
    • removedInput schema / properties / cache_hit_ratio
      Removed value: -{
      -  "default": 0,
      -  "description": "Current prefix cache hit ratio (0.0 to 1.0)",
      -  "type": "number"
      -}
    • addedInput schema / properties / cold_start_cache_write
      Added value: +{
      +  "default": false,
      +  "type": "boolean"
      +}
    • addedInput schema / properties / completion_tokens
      Added value: +{
      +  "maximum": 9007199254740991,
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • removedInput schema / properties / expected_output_tokens
      Removed value: -{
      -  "default": 4000,
      -  "description": "Expected completion token count",
      -  "type": "number"
      -}
    • changedInput schema / properties / model / description
      Previous value: -"Any model ID (e.g. zhipu/glm-5v-turbo, openai/gpt-4.1, claude-3-7-sonnet, gemini-2.5-pro)"New value: +"Model ID from list_supported_models (gpt-6-1-sol, claude-haiku-5-5, claude-sonnet-5-5, claude-opus-5-5, gpt-6-luna)"
    • addedInput schema / properties / pass_rate
      Added value: +{
      +  "default": 0.96,
      +  "exclusiveMinimum": 0,
      +  "maximum": 1,
      +  "type": "number"
      +}
    • removedInput schema / properties / prompt_tokens / description
      Removed value: -"Input prompt token count"
    • addedInput schema / properties / prompt_tokens / maximum
      Added value: +9007199254740991
    • addedInput schema / properties / prompt_tokens / minimum
      Added value: +0
    • changedInput schema / properties / prompt_tokens / type
      Previous value: -"number"New value: +"integer"
    • addedInput schema / properties / request_id
      Added value: +{
      +  "description": "Optional trace ID (1..64 alphanumeric/underscore/hyphen chars).",
      +  "maxLength": 64,
      +  "pattern": "^[a-zA-Z0-9_-]{1,64}$",
      +  "type": "string"
      +}
    • addedInput schema / properties / retry_rate
      Added value: +{
      +  "default": 0.05,
      +  "maximum": 1,
      +  "minimum": 0,
      +  "type": "number"
      +}
    • addedInput schema / properties / routed_cache_hit_rate
      Added value: +{
      +  "maximum": 1,
      +  "minimum": 0,
      +  "type": "number"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "model",
      -  "prompt_tokens"
      -]New value: +[
      +  "model",
      +  "prompt_tokens",
      +  "completion_tokens"
      +]
  6. Changed18 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • removedInput schema / properties / allow_async_batch
      Removed value: -{
      -  "default": true,
      -  "type": "boolean"
      -}
    • removedInput schema / properties / budget_gate_usd
      Removed value: -{
      -  "default": 0.06,
      -  "minimum": 0,
      -  "type": "number"
      -}
    • removedInput schema / properties / cache_hit_rate
      Removed value: -{
      -  "default": 0.4,
      -  "maximum": 1,
      -  "minimum": 0,
      -  "type": "number"
      -}
    • addedInput schema / properties / cache_hit_ratio
      Added value: +{
      +  "default": 0,
      +  "description": "Current prefix cache hit ratio (0.0 to 1.0)",
      +  "type": "number"
      +}
    • removedInput schema / properties / cold_start_cache_write
      Removed value: -{
      -  "default": false,
      -  "type": "boolean"
      -}
    • removedInput schema / properties / completion_tokens
      Removed value: -{
      -  "maximum": 9007199254740991,
      -  "minimum": 0,
      -  "type": "integer"
      -}
    • addedInput schema / properties / expected_output_tokens
      Added value: +{
      +  "default": 4000,
      +  "description": "Expected completion token count",
      +  "type": "number"
      +}
    • changedInput schema / properties / model / description
      Previous value: -"Model ID from list_supported_models (gpt-6-1-sol, claude-haiku-5-5, claude-sonnet-5-5, claude-opus-5-5, gpt-6-luna)"New value: +"Any model ID (e.g. zhipu/glm-5v-turbo, openai/gpt-4.1, claude-3-7-sonnet, gemini-2.5-pro)"
    • removedInput schema / properties / pass_rate
      Removed value: -{
      -  "default": 0.96,
      -  "exclusiveMinimum": 0,
      -  "maximum": 1,
      -  "type": "number"
      -}
    • addedInput schema / properties / prompt_tokens / description
      Added value: +"Input prompt token count"
    • removedInput schema / properties / prompt_tokens / maximum
      Removed value: -9007199254740991
    • removedInput schema / properties / prompt_tokens / minimum
      Removed value: -0
    • changedInput schema / properties / prompt_tokens / type
      Previous value: -"integer"New value: +"number"
    • removedInput schema / properties / request_id
      Removed value: -{
      -  "description": "Optional trace ID (1..64 alphanumeric/underscore/hyphen chars).",
      -  "maxLength": 64,
      -  "pattern": "^[a-zA-Z0-9_-]{1,64}$",
      -  "type": "string"
      -}
    • removedInput schema / properties / retry_rate
      Removed value: -{
      -  "default": 0.05,
      -  "maximum": 1,
      -  "minimum": 0,
      -  "type": "number"
      -}
    • removedInput schema / properties / routed_cache_hit_rate
      Removed value: -{
      -  "maximum": 1,
      -  "minimum": 0,
      -  "type": "number"
      -}
    • changedInput schema / required
      Previous value: -[
      -  "model",
      -  "prompt_tokens",
      -  "completion_tokens"
      -]New value: +[
      +  "model",
      +  "prompt_tokens"
      +]
  7. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Beyond the readOnly/idempotent/closed-world annotations, the description discloses that the lookup is deterministic, requires no API keys, and draws on an embedded registry, plus it names the three return fields. It stops short of describing edge-case behavior (unknown model IDs, negative or zero tokens) that would fully round out the disclosure.

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?

Purpose and threshold table are front-loaded, then behavior, then return shape, then usage — a sensible order with no filler sentences. It is dense with parentheses and parenthetical multipliers, making it slightly heavier to parse than necessary, but every sentence carries distinct information.

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 no output schema, the description compensates by naming the returned fields and their value ranges (1.0x vs 2.0x–5.0x). For a two-parameter, keyless, read-only lookup, nothing an agent needs in order to call it correctly is missing.

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, but the description adds real meaning by mapping specific model families to their cliff boundaries (100K Claude, 128K GPT-4o, 200K Gemini, 272K GPT-6.1 Sol) — information absent from the schema, whose model parameter has no enum. It does not add anything further about prompt_tokens beyond confirming direct comparison against the boundary.

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 opening sentence gives a specific verb and resource ('Evaluates whether a prompt token count crosses vendor long-context surcharge thresholds') and enumerates the exact boundaries it tests against. It is clearly distinguishable from compress_and_fold_context, which is named explicitly as the alternative.

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?

The final sentence states when to call it ('before sending large prompts (>90K tokens)') and names the sibling to use instead when the goal is to shrink the prompt rather than measure it. The when/when-not/alternative triad is fully covered.

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