Skip to main content
Glama

Delegate one stage of work to DSH (starts a model request)

dsh_submit_task

Submits a bounded development stage by validating the workspace, creating an isolated task directory, starting an SDK runtime, and returning task/session IDs immediately; use wait/result tools.

Instructions

Validates the workspace against the allowed roots, creates an isolated task directory and DSH_HOME, starts a private SDK runtime process, sends the stage prompt and returns immediately with taskId/sessionId/state. It does NOT wait for the work to finish: use dsh_wait_task and dsh_get_result. May create or modify files inside the workspace.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "workspace": "<workspace>",
      "goal": "<goal>"
    },
    "name": "dsh_submit_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalYesWhat this stage must produce.
contextNoBackground the model needs.
budgetMsNoPer-stage wall-clock budget. Default 300000ms when omitted; explicit shorter/longer values are preserved. For high effort complex tasks consider 600000ms or more. Expiry stops this task SDK process and marks timed_out.
maxTokensNoPer-response output budget, including model reasoning. Default 16384, maximum 32768. Explicit short budgets are preserved, not raised to a floor; values below 2048 get a warning. Output exhaustion is incomplete, not acceptance.
workspaceYesAbsolute path to the task workspace. Must be inside the bridge's allowed roots.
acceptanceNoHow Codex will judge this stage.
autoRepairNoOpt-in same-session repair on failed host verification. Requires protected acceptance files. Stops on success, unchanged failures, limits, permission errors or cancellation.
constraintsNoRules the model must respect.
autoContinueNoBounded same-live-session continuation ONLY after a real provider max_tokens/length turn end. Omission is disabled; deliveryPreset complete enables maxAttempts=2, noProgressLimit=2, totalBudgetMs=3600000. Explicit fields win. Storage/preview truncation, cancel, permission/credential failures, a dead runtime, shutdown and verifier-integrity failures never trigger it.
deliveryPresetNoComplete delivery: high/32768/30min, 10min verification, up to 3 automatic repair stages. Explicit fields override defaults. Requires an independent command and protected acceptance files.
deliverySourceNoExplicit 1.0.7 source scope for reproducible complete/patch delivery. Omit for the legacy observed-changes export.
reasoningEffortNoDefault medium for work. Use explicit low for short diagnostic probes and high for difficult tasks. none is a legacy alias of off; on GOAT off/none maps to low with an explicit warning, without changing provider.
executionProfileNoOptional execution profile. Omit for the legacy no-preset overlay. "native" mounts the minimal agent preset with native tool schemas; "ptc" presents model tools through run_code and is an explicit opt-in only. Any other value is refused before the task directory is created.
verificationCommandNoOptional argv array the BRIDGE runs itself after the stage ends, in the workspace. No shell is involved. Its real exit code is recorded separately from the model report.
verificationTimeoutMsNo
protectedVerificationFilesNoExisting acceptance files, including checker dependencies and fixtures. Bridge pins real paths and SHA-256 before the model starts and checks before/after verification.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.8

TDQS

A4.2/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false and openWorldHint=true, and the description adds real value beyond them: workspace validation against allowed roots, creation of an isolated task directory and DSH_HOME, a private SDK runtime process, and the crucial non-blocking return contract. It also warns 'May create or modify files inside the workspace,' which is the main side effect an agent needs. It stops short of describing concurrency or resource limits beyond what the schema already documents.

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?

Three short sentences, front-loaded with the operation sequence, then the async caveat and routing, then the file side-effect warning. No filler, and every clause carries information an agent needs before calling.

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 16-parameter tool with nested objects and no output schema, the description covers the essential contract: what is created, that it is non-blocking, what it returns, and which siblings to call next. It does not orient the agent to the heavy optional feature families (autoRepair, autoContinue, deliveryPreset, deliverySource), though the schema documents those at high coverage, so the gap is modest.

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 94%, so the schema already carries nearly all parameter meaning; the description adds only indirect hints, such as the allowed-roots constraint on workspace and the taskId/sessionId/state return shape. With no output schema, mentioning returned identifiers has modest value, but it adds no syntax or defaults 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 states a concrete verb chain on a specific resource: validate workspace, create an isolated task directory and DSH_HOME, start an SDK runtime, send the stage prompt, and return taskId/sessionId/state. It also distinguishes itself from the wait/result siblings by declaring that it returns immediately, so an agent can tell it apart without opening the schema.

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?

It clearly routes the agent forward: 'It does NOT wait for the work to finish: use dsh_wait_task and dsh_get_result,' which is explicit next-step guidance. It does not say when to prefer this over adjacent entry points such as dsh_continue_task or dsh_submit_review, so the comparative guidance is incomplete.

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