Skip to main content
Glama

PlanExe

by io.github.PlanExeOrg

plan_resume

Resume a failed or stopped plan without discarding completed intermediary files. Plan generation restarts from the first incomplete step, skipping all steps that already produced output files. Use plan_resume when plan_status shows 'failed' or 'stopped' and plan generation was interrupted before completing all steps (network drop, timeout, plan_stop, worker crash). For a full restart or to change model_profile, use plan_retry instead. Only failed or stopped plans can be resumed. Returns PLAN_NOT_FOUND when plan_id is unknown and PLAN_NOT_RESUMABLE when the plan is not in failed or stopped state. Returns PIPELINE_VERSION_MISMATCH when the snapshot was created by a different pipeline version; use plan_retry instead.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
plan_idYesUUID of the failed plan to resume.
model_profileNoModel profile used for the resumed plan. Defaults to baseline.baseline

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
errorNo
stateNoCurrent plan state after resume request.
plan_idNoPlan UUID that was resumed (same ID as the failed or stopped plan).
sse_urlNoOptional completion detector. Run `curl -N <sse_url>` in a background shell — the stream auto-closes when the plan reaches a terminal state (completed/failed/stopped). For structured progress data, use plan_status instead.
resumed_atNoUTC timestamp when the resume request was accepted.
resume_countNoNumber of times this plan has been resumed.
model_profileNoModel profile assigned to the resumed run.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • changedOutput schema / properties / sse_url / description
      Previous value: -"Optional completion detector. Run `curl -N <sse_url>` in a background shell — the stream auto-closes when the plan reaches a terminal state (completed/failed). For structured progress data, use plan_status instead."New value: +"Optional completion detector. Run `curl -N <sse_url>` in a background shell — the stream auto-closes when the plan reaches a terminal state (completed/failed/stopped). For structured progress data, use plan_status instead."
  2. Changed2 schema fields changed
    • changedOutput schema / properties / plan_id / description
      Previous value: -"Plan UUID that was resumed (same ID as the failed plan)."New value: +"Plan UUID that was resumed (same ID as the failed or stopped plan)."
    • changedOutput schema / properties / state / anyOf
      Previous value: -[
-  {
-    "enum": [
-      "pending",
-      "processing",
-      "completed",
-      "failed"
-    ],
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "enum": [
+      "pending",
+      "processing",
+      "completed",
+      "failed",
+      "stopped"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
  3. Added

TDQS

A4.5/5.0
Behavior5/5

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

The description provides rich behavioral detail beyond the annotations: it explains that completed files are not discarded, generation resumes from the first incomplete step, and it lists specific error codes (PLAN_NOT_FOUND, PLAN_NOT_RESUMABLE, PIPELINE_VERSION_MISMATCH) with guidance for the version mismatch case. This significantly exceeds the annotation flags and gives the agent a clear picture of the tool's side effects and failure modes.

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 description is a solid paragraph of seven sentences, each sentence contributing useful information (purpose, mechanics, usage conditions, alternatives, constraints, and errors). It is not as tight as a two-sentence description, but it remains well-structured and free of filler, making it easy to parse.

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?

With a 2-parameter schema fully described and an output schema present, the description covers all essential aspects: purpose, when to use, alternative tools, state constraints, and error conditions. It does not describe the exact return structure, but that is adequately delegated to the output schema. Minor gaps like explicit permission prerequisites are absent, but the error handling and context signals make the tool well-understood.

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?

The input schema already covers both parameters (plan_id and model_profile) with clear descriptions, achieving 100% schema coverage. The tool description adds little beyond the schema—it references model_profile only when directing users to plan_retry for changes, which reinforces but does not extend the schema semantics. Baseline 3 is appropriate.

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 clearly identifies the tool's purpose: resuming a failed or stopped plan while preserving completed intermediate files. It also distinguishes itself from plan_retry by stating that plan_retry is for full restarts or model_profile changes, which helps an agent differentiate between the two.

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 description explicitly states when to use plan_resume: when plan_status shows 'failed' or 'stopped' and interruption occurred before all steps completed. It also provides a clear alternative, plan_retry, for full restarts or changing model_profile, and specifies that only failed or stopped plans can be resumed.

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

All PlanExe toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.6/5.0
Disambiguation5/5

Each tool has a distinct, non-overlapping purpose within the PlanExe workflow. For example, example_plans and example_prompts serve different preparatory functions, while plan_create, plan_status, plan_stop, plan_resume, and plan_retry handle distinct lifecycle stages of plan generation. No tools appear to duplicate functionality, making selection clear for an agent.

Naming Consistency5/5

Tool names follow a highly consistent verb_noun pattern throughout, with all tools using snake_case and clear action-object pairs (e.g., plan_create, plan_status, plan_stop). The naming is predictable and readable, with no deviations in style or convention across the set.

Tool Count5/5

With 11 tools, the server is well-scoped for its purpose of generating and managing strategic project plans. Each tool serves a specific role in the workflow, from preparation (example_prompts, model_profiles) to creation (plan_create), monitoring (plan_status), lifecycle management (plan_stop, plan_resume, plan_retry), and feedback (send_feedback). The count is appropriate and avoids bloat or gaps.

Completeness5/5

The tool set provides complete coverage for the plan generation domain, including CRUD-like operations (create, list, status, stop, resume, retry) and supporting functions (examples, model selection, file retrieval, feedback). There are no obvious gaps; agents can handle the entire lifecycle from prompt drafting to plan retrieval and error recovery without dead ends.

Resources