Skip to main content
Glama

rigor_execute

Execute a structured workflow end-to-end. Call rigor_plan first (free) to preview the step sequence and cost estimate before committing credits. Classifies the task, selects the optimal tool sequence, and executes each step with the right LLM model. Returns a complete deliverable — solution designs, competitive analyses, governance documents, and more. Supports SSE streaming for real-time progress, webhook callback, or polling. For atomic work — classification, scoring, ranking, entity extraction, query parsing — set preferences.execution to 'direct' and declare preferences.output_contract to get validated JSON records from a single call, routed to the cheapest model that holds the schema.

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": "rigor_execute"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo"interactive" returns interactive_waiting and runs 1 step per POST /api/rigor/step; otherwise "full".
contextNoAdditional context for the workflow. Persisted with a plan, so an execute by workflow_id inherits it unless it sends its own.
agent_idNoYour own label for the calling agent, at most 200 characters. Recorded on the workflow and its cost rows; never used for routing or authorization.
deliveryNoHow you receive progress and the result. Over REST the default is sse; over MCP it is polling, because most MCP clients cannot read a stream.
languageNoBCP 47 language code for the deliverable (for example "fr", "ja", "pt-BR"). Overrides the organization default.
task_typeNoOptional hint to bypass automatic classification. Passing it also removes the slowest classification tiers from the critical path, so send it whenever you know the shape. Multi-step deliverable types: solution_design, requirements_analysis, code_implementation, code_review, bug_fix, root_cause_analysis, incident_response, deployment_execution, competitive_scan, financial_analysis, research_task, documentation, governance_change, compliance_audit, data_security_assessment, performance_optimization, user_story_definition, implementation_prompt_generation. Atomic single-call types, which auto-select direct execution: tag, score, rerank, compose, extract_entities, parse_query, quick_research, quick_classification, quick_extraction, quick_scoring. GET /api/rigor/task-types lists the full vocabulary with each type's shape.
preferencesNoOptional workflow preferences. The same shape on plan and execute; a plan stores them, and an execute by workflow_id inherits them.
workflow_idNoThe workflow_id (wr_…) a plan call returned. Runs that stored plan without re-planning. Required when task_description is absent.
workflow_idsNoSeveral planned workflow ids (from a multi-intent plan) to run without re-planning.
context_fieldsNoOptional, with prior_workflow_id: the fields to carry over. Pass ["full_step_results"] for every step output in full.
task_descriptionNoNatural language description of the task, at least 2 words and at most 4,000 characters (200,000 across it and context.additional_context when task_type is compose). Be specific: include what you want produced, constraints, and context. Example: 'Design a caching layer for our API gateway with Redis integration.' Required when workflow_id is absent.
prior_workflow_idNoOptional: the workflow_id (wr_…) of a finished workflow in your workspace to build on. Its results are passed to this run as context. It is charged as a new run at the normal quote.
refresh_connectionsNoRefresh your MCP connection state before the run starts. Defaults to true; a failed refresh never blocks the run.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / preferences / properties / output_contract / description
      Previous value: -"Only read when execution is \"direct\". Declares the JSON shape you want back, so the answer is generated against your schema (Anthropic forced tool-use, or an OpenAI-compatible json_schema response format) and validated against it before return, instead of returned as prose you have to parse. A conforming run also skips the quality-review call, costing 1 LLM call rather than 2. The schema is closed: a record carrying an undeclared key is rejected exactly like one missing a required key. Persists with the plan, so a later execute against the stored workflow_id inherits it. Not the same shape as the inference gateway's output_contract, which carries the items an answer must account for rather than a record schema."New value: +"Only read when execution is \"direct\". Declares the JSON shape you want back, so the answer is generated against your schema (Anthropic forced tool-use, or an OpenAI-compatible json_schema response format) and validated against it before return, instead of returned as prose you have to parse. A conforming run also skips the quality-review call, costing 1 LLM call rather than 2. The schema is closed: a record carrying an undeclared key is rejected exactly like one missing a required key. An answer that breaks the contract is retried once with the violations as feedback; if it still breaks it, the run fails and is refunded, never billed. A contract no answer can meet (an empty enum, a minimum above its maximum, duplicate field names) is refused with 400 before any call, and an organisation with 10 refunded contract failures in 24 hours gets 429 until the oldest leaves the window. Persists with the plan, so a later execute against the stored workflow_id inherits it; that execute may omit the field or repeat it unchanged, and a different contract there is refused with 400 (plan again to change it). Not the same shape as the inference gateway's output_contract, which carries the items an answer must account for rather than a record schema."
  2. Changed36 schema fields changed
    • addedInput schema / properties / agent_id
      Added value: +{
      +  "description": "Your own label for the calling agent, at most 200 characters. Recorded on the workflow and its cost rows; never used for routing or authorization.",
      +  "maxLength": 200,
      +  "type": "string"
      +}
    • changedInput schema / properties / context / description
      Previous value: -"Additional context for the workflow."New value: +"Additional context for the workflow. Persisted with a plan, so an execute by workflow_id inherits it unless it sends its own."
    • changedInput schema / properties / context / properties / additional_context / description
      Previous value: -"Free-form context the workflow steps can reference."New value: +"Free-form context the workflow steps can reference, at most 16,000 characters (more for compose, see task_description)."
    • changedInput schema / properties / delivery / description
      Previous value: -"Delivery method. Default: polling (MCP clients typically can't handle SSE)."New value: +"How you receive progress and the result. Over REST the default is sse; over MCP it is polling, because most MCP clients cannot read a stream."
    • changedInput schema / properties / delivery / properties / method / description
      Previous value: -"sse | webhook | polling. Default for MCP: polling."New value: +"sse streams events; polling returns at once with poll_url; webhook posts the events in the webhooks section to webhook_url. Interactive delivery, which available_modes also lists, is chosen with mode, not here."
    • addedInput schema / properties / delivery / properties / method / enum
      Added value: +[
      +  "sse",
      +  "polling",
      +  "webhook"
      +]
    • changedInput schema / properties / delivery / properties / webhook_url / description
      Previous value: -"Required if method is webhook. Must be HTTPS."New value: +"Required when method is webhook. HTTPS, resolving only to public addresses."
    • addedInput schema / properties / delivery / properties / webhook_url / format
      Added value: +"uri"
    • addedInput schema / properties / delivery / properties / webhook_url / maxLength
      Added value: +2048
    • addedInput schema / properties / language
      Added value: +{
      +  "description": "BCP 47 language code for the deliverable (for example \"fr\", \"ja\", \"pt-BR\"). Overrides the organization default.",
      +  "type": "string"
      +}
    • addedInput schema / properties / mode
      Added value: +{
      +  "description": "\"interactive\" returns interactive_waiting and runs 1 step per POST /api/rigor/step; otherwise \"full\".",
      +  "enum": [
      +    "full",
      +    "interactive"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / preferences / description
      Previous value: -"Optional workflow preferences."New value: +"Optional workflow preferences. The same shape on plan and execute; a plan stores them, and an execute by workflow_id inherits them."
    • addedInput schema / properties / preferences / properties / add_frameworks
      Added value: +{
      +  "description": "Frameworks to inject into the sequence: a name, or { name, before_step } to choose the position.",
      +  "items": {
      +    "anyOf": [
      +      {
      +        "type": "string"
      +      },
      +      {
      +        "properties": {
      +          "before_step": {
      +            "description": "Zero-based index into the filtered sequence before which to insert it.",
      +            "minimum": 0,
      +            "type": "integer"
      +          },
      +          "name": {
      +            "description": "Framework display name or ID.",
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "name",
      +          "before_step"
      +        ],
      +        "type": "object"
      +      }
      +    ]
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / preferences / properties / approval_before_step
      Added value: +{
      +  "description": "Zero-based step indices where approval gates are inserted.",
      +  "items": {
      +    "minimum": 0,
      +    "type": "integer"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / preferences / properties / cache_prefix_chars
      Added value: +{
      +  "description": "How many leading characters of task_description stay the same across your calls. Direct execution marks that prefix for the provider's prompt cache, so repeated calls read it from cache. Absent or 0 declares nothing.",
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • changedInput schema / properties / preferences / properties / execution / description
      Previous value: -"Set to 'direct' to compose the plan's content frameworks into a single LLM call and route cost-first, using a per-task-type model floor that moves when a cheaper model earns the work. Research steps, process steps (classification-verify, review protocol, synthesis) and the quality review each remain separate calls, so this is not a one-call-per-workflow guarantee: for atomic task types, which have a single content framework, the call count matches standard execution and the saving is the model. Supplying output_contract replaces the quality-review call with deterministic validation, which is one fewer call. No intermediate outputs. Available at every tier. Auto-selected for atomic task types when no execution preference is given. Falls back to standard execution when combined with require_approval or interactive mode, or when the plan exceeds the composition size limit. With attachments or prior_workflow_id, the workflow runs as standard execution instead, so the attachments and the earlier results are applied."New value: +"Set to 'direct' to compose the plan's content frameworks into a single LLM call and route cost-first, using a per-task-type model floor that moves when a cheaper model earns the work. Research steps, process steps (classification-verify, review protocol, synthesis) and the quality review each remain separate calls, so this is not a one-call-per-workflow guarantee: for atomic task types, which have a single content framework, the call count matches standard execution and the saving is the model. Supplying output_contract replaces the quality-review call with deterministic validation, which is one fewer call. No intermediate outputs. Available at every tier. Auto-selected for atomic task types when no execution preference is given. Some atomic task types (for example cluster) run in direct mode only and are refused with 422 direct_mode_unavailable rather than falling back. Others fall back to standard execution when combined with require_approval or interactive mode, or when the plan exceeds the composition size limit. With attachments or prior_workflow_id, the workflow runs as standard execution instead, so the attachments and the earlier results are applied."
    • addedInput schema / properties / preferences / properties / independent_of
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Model creators and model ids that must not receive this workflow's content (for example when it grades output one model family produced). Covers every model call Rigor makes for the workflow: planning (classification, intent extraction, title), every step, research agents, review and quality checks, retrieval over files attached to the workflow, and per-step quality grading after the workflow ends. Not covered: processing when a file is uploaded (text extraction, audio and video transcription, indexing) and POST /api/rigor/enhance. A hard constraint: an excluded model, or one whose creator cannot be confirmed, is skipped; a step with no model left fails the workflow with policy_rule no_independent_model and is refunded; an optional planning or grading call with no model left is skipped. Not relaxed by any workspace policy enforcement mode. Fixed when the workflow is planned: an execute call on a stored plan that sends a different value is refused with 400; entry order does not matter.",
      +  "minProperties": 1,
      +  "properties": {
      +    "families": {
      +      "description": "Model creators: anthropic, deepseek, google, minimax, mistral, moonshot, openai, qwen, xai or zhipu. Case does not matter; any other name is refused with 400.",
      +      "items": {
      +        "maxLength": 64,
      +        "pattern": "^[A-Za-z0-9][A-Za-z0-9._-]*$",
      +        "type": "string"
      +      },
      +      "maxItems": 20,
      +      "type": "array"
      +    },
      +    "models": {
      +      "description": "Model ids. A dated version or -latest alias of a listed id is excluded too.",
      +      "items": {
      +        "maxLength": 200,
      +        "minLength": 1,
      +        "type": "string"
      +      },
      +      "maxItems": 20,
      +      "type": "array"
      +    }
      +  },
      +  "type": "object"
      +}
    • changedInput schema / properties / preferences / properties / max_budget_usd / description
      Previous value: -"Spending ceiling in USD. If the plan's quote is still above it after Rigor fits the plan (cheaper models, optional steps dropped), rigor_plan returns a max_budget_exceeded warning and rigor_execute refuses with 402 max_budget_exceeded before anything runs or is charged."New value: +"Spending ceiling in USD. If the plan's quote is still above it after Rigor fits the plan (cheaper models, optional steps dropped), the plan returns a max_budget_exceeded warning and execute refuses with 402 max_budget_exceeded before anything runs or is charged."
    • addedInput schema / properties / preferences / properties / max_budget_usd / exclusiveMinimum
      Added value: +0
    • addedInput schema / properties / preferences / properties / model_preference
      Added value: +{
      +  "description": "LLM model selection bias.",
      +  "enum": [
      +    "quality_first",
      +    "cost_optimized",
      +    "balanced"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / preferences / properties / only_frameworks
      Added value: +{
      +  "description": "Restrict the plan to these frameworks (display name or ID). Applied before skip_frameworks; unknown names are reported in warnings, and if none resolves the request is refused with 400 UNKNOWN_FRAMEWORK.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • changedInput schema / properties / preferences / properties / output_contract / description
      Previous value: -"Only read when execution is \"direct\". Declares the JSON shape you want back, so the answer is generated against your schema and validated against it before return, instead of returned as prose you have to parse. A conforming run also skips the quality-review call, costing 1 LLM call rather than 2. The schema is closed: a record carrying an undeclared key is rejected exactly like one missing a required key."New value: +"Only read when execution is \"direct\". Declares the JSON shape you want back, so the answer is generated against your schema (Anthropic forced tool-use, or an OpenAI-compatible json_schema response format) and validated against it before return, instead of returned as prose you have to parse. A conforming run also skips the quality-review call, costing 1 LLM call rather than 2. The schema is closed: a record carrying an undeclared key is rejected exactly like one missing a required key. Persists with the plan, so a later execute against the stored workflow_id inherits it. Not the same shape as the inference gateway's output_contract, which carries the items an answer must account for rather than a record schema."
    • addedInput schema / properties / preferences / properties / output_contract / properties / fields / items / properties / items
      Added value: +{
      +  "description": "The element schema, a field entry of this same shape. Only read when type is \"array\".",
      +  "type": "object"
      +}
    • addedInput schema / properties / preferences / properties / output_contract / properties / fields / items / properties / properties
      Added value: +{
      +  "description": "The nested field entries, each of this same shape. Only read when type is \"object\".",
      +  "items": {
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / preferences / properties / require_approval
      Added value: +{
      +  "description": "Pause at pending_approval before the final step.",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / preferences / properties / rigor_level / description
      Previous value: -"quick | standard (default) | thorough. Controls analysis depth and cost."New value: +"Review depth. Default auto-detected from the task type. Controls analysis depth and cost."
    • addedInput schema / properties / preferences / properties / rigor_level / enum
      Added value: +[
      +  "quick",
      +  "standard",
      +  "thorough"
      +]
    • addedInput schema / properties / preferences / properties / skip_frameworks
      Added value: +{
      +  "description": "Frameworks to exclude, by the display name the plan shows or by ID, any case. Unknown names are reported in warnings.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / preferences / properties / tool_scope
      Added value: +{
      +  "description": "Which framework tiers to include.",
      +  "enum": [
      +    "mandatory",
      +    "recommended",
      +    "all"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / preferences / properties / use_connections
      Added value: +{
      +  "description": "Whether the plan may read your connected sources (a GitHub repository, an MCP server). false attaches none; true attaches all. Omitted, a source is attached only when the task is work on code or names a file, your own code, or the source itself.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / refresh_connections
      Added value: +{
      +  "description": "Refresh your MCP connection state before the run starts. Defaults to true; a failed refresh never blocks the run.",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / task_description / description
      Previous value: -"Natural language description of the task, at most 4,000 characters. Be specific — include what you want produced, constraints, and context. Example: 'Design a caching layer for our API gateway with Redis integration.'"New value: +"Natural language description of the task, at least 2 words and at most 4,000 characters (200,000 across it and context.additional_context when task_type is compose). Be specific: include what you want produced, constraints, and context. Example: 'Design a caching layer for our API gateway with Redis integration.' Required when workflow_id is absent."
    • changedInput schema / properties / task_type / description
      Previous value: -"Optional hint to bypass automatic classification. Passing it also removes the slowest classification tiers from the critical path, so send it whenever you know the shape. Multi-step deliverable types: solution_design, requirements_analysis, code_implementation, code_review, bug_fix, root_cause_analysis, incident_response, deployment_execution, competitive_scan, financial_analysis, research_task, documentation, governance_change, compliance_audit, data_security_assessment, performance_optimization, user_story_definition, implementation_prompt_generation. Atomic single-call types, which auto-select direct execution: tag, score, rerank, compose, extract_entities, parse_query, quick_research, quick_classification, quick_extraction, quick_scoring. Call GET /api/rigor/task-types for the full vocabulary with each type's shape."New value: +"Optional hint to bypass automatic classification. Passing it also removes the slowest classification tiers from the critical path, so send it whenever you know the shape. Multi-step deliverable types: solution_design, requirements_analysis, code_implementation, code_review, bug_fix, root_cause_analysis, incident_response, deployment_execution, competitive_scan, financial_analysis, research_task, documentation, governance_change, compliance_audit, data_security_assessment, performance_optimization, user_story_definition, implementation_prompt_generation. Atomic single-call types, which auto-select direct execution: tag, score, rerank, compose, extract_entities, parse_query, quick_research, quick_classification, quick_extraction, quick_scoring. GET /api/rigor/task-types lists the full vocabulary with each type's shape."
    • addedInput schema / properties / workflow_id
      Added value: +{
      +  "description": "The workflow_id (wr_…) a plan call returned. Runs that stored plan without re-planning. Required when task_description is absent.",
      +  "type": "string"
      +}
    • addedInput schema / properties / workflow_ids
      Added value: +{
      +  "description": "Several planned workflow ids (from a multi-intent plan) to run without re-planning.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • removedInput schema / required
      Removed value: -[
      -  "task_description"
      -]
  3. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -{
      -  "properties": {
      -    "available_modes": {
      -      "items": {
      -        "type": "string"
      -      },
      -      "type": "array"
      -    },
      -    "delivery_mode": {
      -      "type": "string"
      -    },
      -    "estimated_credits": {
      -      "type": "number"
      -    },
      -    "execution": {
      -      "description": "Present with value 'direct' when direct execution ran. Absent for standard multi-call execution.",
      -      "type": "string"
      -    },
      -    "execution_fallback": {
      -      "description": "True when you explicitly requested direct execution and it could not be honoured — the workflow ran as standard multi-call instead. Never set for an auto-selected attempt, since you did not ask.",
      -      "type": "boolean"
      -    },
      -    "ok": {
      -      "type": "boolean"
      -    },
      -    "poll_url": {
      -      "type": "string"
      -    },
      -    "status": {
      -      "type": "string"
      -    },
      -    "task_type": {
      -      "type": "string"
      -    },
      -    "value_class": {
      -      "type": "string"
      -    },
      -    "workflow_id": {
      -      "type": "string"
      -    }
      -  },
      -  "type": "object"
      -}New value: +null
  4. Changed3 schema fields changed
    • addedInput schema / properties / context_fields
      Added value: +{
      +  "description": "Optional, with prior_workflow_id: the fields to carry over. Pass [\"full_step_results\"] for every step output in full.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • changedInput schema / properties / preferences / properties / execution / description
      Previous value: -"Set to 'direct' to compose the plan's content frameworks into a single LLM call and route cost-first, using a per-task-type model floor that moves when a cheaper model earns the work. Research steps, process steps (classification-verify, review protocol, synthesis) and the quality review each remain separate calls, so this is not a one-call-per-workflow guarantee: for atomic task types, which have a single content framework, the call count matches standard execution and the saving is the model. Supplying output_contract replaces the quality-review call with deterministic validation, which is one fewer call. No intermediate outputs. Available at every tier. Auto-selected for atomic task types when no execution preference is given. Falls back to standard execution when combined with require_approval or interactive mode, or when the plan exceeds the composition size limit. Attachments and prior_workflow_id chaining are NOT applied — use standard execution for those."New value: +"Set to 'direct' to compose the plan's content frameworks into a single LLM call and route cost-first, using a per-task-type model floor that moves when a cheaper model earns the work. Research steps, process steps (classification-verify, review protocol, synthesis) and the quality review each remain separate calls, so this is not a one-call-per-workflow guarantee: for atomic task types, which have a single content framework, the call count matches standard execution and the saving is the model. Supplying output_contract replaces the quality-review call with deterministic validation, which is one fewer call. No intermediate outputs. Available at every tier. Auto-selected for atomic task types when no execution preference is given. Falls back to standard execution when combined with require_approval or interactive mode, or when the plan exceeds the composition size limit. With attachments or prior_workflow_id, the workflow runs as standard execution instead, so the attachments and the earlier results are applied."
    • addedInput schema / properties / prior_workflow_id
      Added value: +{
      +  "description": "Optional: the workflow_id (wr_…) of a finished workflow in your workspace to build on. Its results are passed to this run as context. It is charged as a new run at the normal quote.",
      +  "type": "string"
      +}
  5. Changed1 schema field changed
    • changedInput schema / properties / task_description / description
      Previous value: -"Natural language description of the task. Be specific — include what you want produced, constraints, and context. Example: 'Design a caching layer for our API gateway with Redis integration.'"New value: +"Natural language description of the task, at most 4,000 characters. Be specific — include what you want produced, constraints, and context. Example: 'Design a caching layer for our API gateway with Redis integration.'"
  6. Changed1 schema field changed
    • changedInput schema / properties / preferences / properties / max_budget_usd / description
      Previous value: -"Maximum budget in USD."New value: +"Spending ceiling in USD. If the plan's quote is still above it after Rigor fits the plan (cheaper models, optional steps dropped), rigor_plan returns a max_budget_exceeded warning and rigor_execute refuses with 402 max_budget_exceeded before anything runs or is charged."
  7. Changed1 schema field changed
    • changedInput schema / properties / task_type / description
      Previous value: -"Optional hint to bypass automatic classification. Passing it also removes the slowest classification tiers from the critical path, so send it whenever you know the shape. Multi-step deliverable types: solution_design, requirements_analysis, code_implementation, code_review, bug_fix, root_cause_analysis, incident_response, deployment_execution, competitive_scan, financial_analysis, research_task, documentation, governance_change, compliance_audit, data_security_assessment, performance_optimization, user_story_definition, implementation_prompt_generation. Atomic single-call types, which auto-select direct execution: tag, score, rerank, extract_entities, parse_query, quick_research, quick_classification, quick_extraction, quick_scoring. Call GET /api/rigor/task-types for the full vocabulary with each type's shape."New value: +"Optional hint to bypass automatic classification. Passing it also removes the slowest classification tiers from the critical path, so send it whenever you know the shape. Multi-step deliverable types: solution_design, requirements_analysis, code_implementation, code_review, bug_fix, root_cause_analysis, incident_response, deployment_execution, competitive_scan, financial_analysis, research_task, documentation, governance_change, compliance_audit, data_security_assessment, performance_optimization, user_story_definition, implementation_prompt_generation. Atomic single-call types, which auto-select direct execution: tag, score, rerank, compose, extract_entities, parse_query, quick_research, quick_classification, quick_extraction, quick_scoring. Call GET /api/rigor/task-types for the full vocabulary with each type's shape."
  8. Changed5 schema fields changed
    • addedInput schema / properties / preferences / properties / execution
      Added value: +{
      +  "description": "Set to 'direct' to compose the plan's content frameworks into a single LLM call and route cost-first, using a per-task-type model floor that moves when a cheaper model earns the work. Research steps, process steps (classification-verify, review protocol, synthesis) and the quality review each remain separate calls, so this is not a one-call-per-workflow guarantee: for atomic task types, which have a single content framework, the call count matches standard execution and the saving is the model. Supplying output_contract replaces the quality-review call with deterministic validation, which is one fewer call. No intermediate outputs. Available at every tier. Auto-selected for atomic task types when no execution preference is given. Falls back to standard execution when combined with require_approval or interactive mode, or when the plan exceeds the composition size limit. Attachments and prior_workflow_id chaining are NOT applied — use standard execution for those.",
      +  "enum": [
      +    "direct"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / preferences / properties / output_contract
      Added value: +{
      +  "description": "Only read when execution is \"direct\". Declares the JSON shape you want back, so the answer is generated against your schema and validated against it before return, instead of returned as prose you have to parse. A conforming run also skips the quality-review call, costing 1 LLM call rather than 2. The schema is closed: a record carrying an undeclared key is rejected exactly like one missing a required key.",
      +  "properties": {
      +    "count": {
      +      "description": "Bounds on the number of entries. Only read when shape is \"array\".",
      +      "properties": {
      +        "max": {
      +          "type": "number"
      +        },
      +        "min": {
      +          "type": "number"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "fields": {
      +      "description": "The schema for 1 record.",
      +      "items": {
      +        "properties": {
      +          "description": {
      +            "description": "Passed to the model as the field's description.",
      +            "type": "string"
      +          },
      +          "enum": {
      +            "description": "Restricts a string field to a fixed set of values.",
      +            "items": {
      +              "type": "string"
      +            },
      +            "type": "array"
      +          },
      +          "maximum": {
      +            "description": "Upper bound for a numeric field.",
      +            "type": "number"
      +          },
      +          "minimum": {
      +            "description": "Lower bound for a numeric field.",
      +            "type": "number"
      +          },
      +          "name": {
      +            "description": "The JSON key.",
      +            "type": "string"
      +          },
      +          "required": {
      +            "description": "Defaults to true. Set false for a field that may be absent.",
      +            "type": "boolean"
      +          },
      +          "type": {
      +            "description": "The value's type.",
      +            "enum": [
      +              "string",
      +              "number",
      +              "integer",
      +              "boolean",
      +              "array",
      +              "object"
      +            ],
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "name",
      +          "type"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "selection": {
      +      "description": "Use when you want the model to over-generate candidates and Rigor to sort, threshold, and cap them before the count bounds are checked.",
      +      "properties": {
      +        "maxCount": {
      +          "type": "number"
      +        },
      +        "minCount": {
      +          "type": "number"
      +        },
      +        "minScore": {
      +          "type": "number"
      +        },
      +        "scoreField": {
      +          "type": "string"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "shape": {
      +      "description": "\"object\" for 1 record, \"array\" for 1 entry per input item.",
      +      "enum": [
      +        "object",
      +        "array"
      +      ],
      +      "type": "string"
      +    },
      +    "task_type": {
      +      "description": "Your own label for the work. Echoed into telemetry. Not read as a framework name and does not change routing.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "task_type",
      +    "shape",
      +    "fields"
      +  ],
      +  "type": "object"
      +}
    • changedInput schema / properties / task_type / description
      Previous value: -"Optional hint to bypass automatic classification. Values: solution_design, requirements_analysis, code_implementation, code_review, bug_fix, root_cause_analysis, incident_response, deployment_execution, competitive_scan, financial_analysis, research_task, documentation, governance_change, compliance_audit, data_security_assessment, performance_optimization, user_story_definition, implementation_prompt_generation."New value: +"Optional hint to bypass automatic classification. Passing it also removes the slowest classification tiers from the critical path, so send it whenever you know the shape. Multi-step deliverable types: solution_design, requirements_analysis, code_implementation, code_review, bug_fix, root_cause_analysis, incident_response, deployment_execution, competitive_scan, financial_analysis, research_task, documentation, governance_change, compliance_audit, data_security_assessment, performance_optimization, user_story_definition, implementation_prompt_generation. Atomic single-call types, which auto-select direct execution: tag, score, rerank, extract_entities, parse_query, quick_research, quick_classification, quick_extraction, quick_scoring. Call GET /api/rigor/task-types for the full vocabulary with each type's shape."
    • addedOutput schema / properties / execution
      Added value: +{
      +  "description": "Present with value 'direct' when direct execution ran. Absent for standard multi-call execution.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / execution_fallback
      Added value: +{
      +  "description": "True when you explicitly requested direct execution and it could not be honoured — the workflow ran as standard multi-call instead. Never set for an auto-selected attempt, since you did not ask.",
      +  "type": "boolean"
      +}
  9. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "available_modes": {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    "delivery_mode": {
      +      "type": "string"
      +    },
      +    "estimated_credits": {
      +      "type": "number"
      +    },
      +    "ok": {
      +      "type": "boolean"
      +    },
      +    "poll_url": {
      +      "type": "string"
      +    },
      +    "status": {
      +      "type": "string"
      +    },
      +    "task_type": {
      +      "type": "string"
      +    },
      +    "value_class": {
      +      "type": "string"
      +    },
      +    "workflow_id": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  10. Changed5 schema fields changed
    • removedInput schema / properties / preferences / properties / quality_level
      Removed value: -{
      -  "description": "minimum | standard | maximum.",
      -  "type": "string"
      -}
    • addedInput schema / properties / preferences / properties / rigor_level
      Added value: +{
      +  "description": "quick | standard (default) | thorough. Controls analysis depth and cost.",
      +  "type": "string"
      +}
    • removedInput schema / properties / preferences / properties / tool_scope
      Removed value: -{
      -  "description": "mandatory | recommended | all.",
      -  "type": "string"
      -}
    • changedInput schema / properties / task_description / description
      Previous value: -"Natural language description of the task. Be specific."New value: +"Natural language description of the task. Be specific — include what you want produced, constraints, and context. Example: 'Design a caching layer for our API gateway with Redis integration.'"
    • changedInput schema / properties / task_type / description
      Previous value: -"Optional classification hint."New value: +"Optional hint to bypass automatic classification. Values: solution_design, requirements_analysis, code_implementation, code_review, bug_fix, root_cause_analysis, incident_response, deployment_execution, competitive_scan, financial_analysis, research_task, documentation, governance_change, compliance_audit, data_security_assessment, performance_optimization, user_story_definition, implementation_prompt_generation."
  11. Added

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The description adds real behavioral context beyond that: this call spends credits, planning is free, direct mode routes to the cheapest model that holds the schema, and three delivery mechanisms exist. It does not address duplicate-execution/charge behavior on retries or partial-failure outcomes, which matter for a non-idempotent paid operation.

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?

The core action and the cheap-preview prerequisite are front-loaded in the first two sentences, and each subsequent sentence carries distinct information (classification/model routing, delivery modes, atomic-mode branch). The final sentence is long and heavily packed with sub-conditions, which slows scanning, but little of it is filler.

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 13-parameter, nested-schema, no-output-schema tool, the description covers cost, routing, delivery and the plan-first pattern well. It omits one invocation-critical constraint — that at least one of workflow_id, workflow_ids or task_description must be supplied — which an agent only learns from the schema, and it doesn't say what rigor_status or rigor_workflows offer for the polling path it advertises.

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% across all 13 parameters, so the baseline is 3. The description still adds navigational value by surfacing the two preferences that most change behavior (execution='direct' and output_contract) and explaining the payload they unlock, helping an agent prioritize among a large nested schema rather than treating all parameters as equal.

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?

"Execute a structured workflow end-to-end" pairs a specific verb with a specific resource, then names what the tool internally does (classifies the task, selects the tool sequence, executes each step) and what it returns (solution designs, competitive analyses, governance documents). It also explicitly carves out the sibling boundary by saying rigor_plan is the preview-only step, so an agent can distinguish the two 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?

It gives an explicit prerequisite sequence ("Call rigor_plan first (free) ... before committing credits") and an explicit branch for a different work shape (atomic work → set preferences.execution to 'direct' and declare output_contract). Both the alternative and the condition that selects it are stated, not implied.

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