DevTune MCP

devtune_run_agent

Trigger a metered manual managed-agent run through DevTune’s evidence- and credit-checked dispatch path. Refuses with agent_evidence_unavailable, before any credits are spent, when the project has nothing this agent can read, and with target_page_refused when targetPage names no page the agent can work on.

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": {
      "agentKey": "<agentKey>",
      "requestIdempotencyKey": "<requestIdempotencyKey>"
    },
    "name": "devtune_run_agent"
  }
}

Input Schema

Name	Required	Description
`modelId`	No	Optional available model-catalog identifier.
`agentKey`	Yes	Roster or custom agent key to run.
`targetPage`	No	Optional page the run works on, for agents that brief one page (citability-editor): an absolute URL, or a path such as /pricing on a tracked domain. The run briefs that page and no other.
`instructions`	No	Optional focus for this run.
`requestIdempotencyKey`	Yes	Required caller-generated UUID for idempotent retries.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 11, 2026

addedInput schema / properties / targetPage

Added value: +{
+  "description": "Optional page the run works on, for agents that brief one page (citability-editor): an absolute URL, or a path such as /pricing on a tracked domain. The run briefs that page and no other.",
+  "maxLength": 2048,
+  "minLength": 1,
+  "type": "string"
+}

First observedSep 9, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Beyond the annotations, the description discloses the cost model ('metered ... credits'), the precondition of readable project evidence, and two named refusal outcomes (agent_evidence_unavailable, target_page_refused) that occur before credits are spent. It does not say what a successful dispatch returns or how to follow the run, which is the main remaining gap.

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?

Two sentences, no filler, with the action and the metering/cost constraint front-loaded. The refusal clauses are compressed into a slightly dense second sentence but every clause carries information.

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

Completeness3/5

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

For a trigger tool with no output schema and no annotations about side effects, the description should indicate what comes back (e.g. a run id or record to poll via devtune_get_agent_run). That is missing, so an agent knows the preconditions but not the post-conditions.

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

Parameters3/5

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

Schema description coverage is 100%, so all five parameters are already documented. The description adds only the refusal semantics for targetPage ('names no page the agent can work on') and the cost implication of a run; agentKey, modelId, instructions and the idempotency key get no added meaning.

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?

States a specific verb and resource: 'Trigger a ... managed-agent run ... through DevTune's dispatch path.' The modifier 'manual' and 'metered' distinguishes it from the read-side siblings devtune_get_agent_run and devtune_list_agent_runs, which only retrieve runs.

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

Usage Guidelines3/5

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

The word 'manual' implies this is the imperative entry point versus scheduled/list variants, but no sibling is named and no explicit when-to-use / when-not-to-use rule is given. With roughly 90 siblings, the agent is left to infer the selection rule rather than being routed.

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

All DevTune MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?