start_jobStep 2: queue a job whose deck tarball has been uploaded. A GPU pod is launched; billing starts when it reports running.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Job id, e.g. MDJOB-20260907-3F200C |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses important behavioral consequences beyond what annotations provide: it launches a GPU pod and starts billing when the pod reports running. This adds context about side effects and cost, which is valuable for an agent deciding whether to invoke it. It does not contradict the annotations (readOnlyHint=false, non-idempotent, non-destructive).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the action and sequence step, and includes only essential details (precondition, pod launch, billing). There is no fluff or redundancy, making it highly efficient for an agent to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the key prerequisites (uploaded tarball), the action, and side effects (pod launch, billing). It lacks explicit mention of what happens on failure or how to check status, but the sibling tools (job_status, job_log) and the non-idempotent annotation cover those aspects. For a simple one-parameter tool, this is fairly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides full coverage for the single 'id' parameter with an example format. The description does not add any extra meaning about the parameter itself, so it relies on the schema. Baseline of 3 is appropriate since schema coverage is 100%.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (queue a job) and the resource (an uploaded job's deck tarball). It positions it as 'Step 2', which helps differentiate it from siblings like create_job or submit_job, but it does not explicitly name those alternatives. The purpose is specific enough to avoid confusion with cancel_job or delete_results.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies a precondition (deck tarball already uploaded) and a sequence ('Step 2'), which gives some usage context. However, it does not explicitly state when not to use this tool or point to alternatives like submit_job for creating a new job. The guidance is implicit rather than explicit, so it is adequate but not strong.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool serves a distinct purpose: account and capabilities cover account/configuration info, while create_job, start_job, and submit_job represent clearly differentiated job submission stages. Monitoring, results, cancellation, and deletion tools are all non-overlapping.
Tool names mostly follow a clear snake_case verb_noun pattern (cancel_job, create_job, delete_results, list_jobs, start_job, submit_job). A few noun-only names like account, capabilities, job_status, and job_results deviate slightly, but the pattern remains recognizable and predictable.
With 12 tools, the set covers the full job lifecycle without being bloated. Each tool maps to a meaningful operation, and the count is well within the typical 3-15 range for a domain-specific server.
The tool surface covers the necessary workflow: checking account/capabilities, submitting and starting jobs, monitoring status/logs, retrieving results, canceling jobs, and deleting results. No essential operation for the stated GPU job management domain appears missing.