Skip to main content
Glama

job_status

Retrieve results for pending generation jobs by passing the original job handles. Get finished URLs, re-check pending ones, or report terminal failures without creating new jobs.

Instructions

Retrieve a long-running generation that was submitted earlier but hasn't finished — any result from a generation tool that came back as {status:"pending", ...} (a job handle, not media). Pass the exact pending handle object(s) in jobs; NEVER re-submit a pending job with the tool that created it — that starts (and bills) a new one. Each job comes back one of three ways: finished (a hosted URL plus a local file path); still pending ({status:"pending", ...}), in which case call job_status again with the same handle after a short wait; or failed, carrying ok: false and an error. A failed job is terminal — it will never finish, so report the error and never poll or re-submit that handle. A batch can mix all three, so read every entry in results rather than the top-level counters alone. This works for any kind of pending generation and only rejoins an existing job — it neither starts nor bills a new one.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
jobsYesThe pending job handle object(s) to retrieve — each exactly as returned by a prior video_generate / job_status call. Add more than one to retrieve a batch in one call.
Behavior5/5

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

No annotations are present, so the description carries full responsibility for behavioral disclosure. It thoroughly explains that jobs can finish, remain pending, or fail; that failure is terminal; that batches mix results; and that the tool has no billing side-effects. This is exemplary transparency.

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?

The description is long but every sentence earns its place. It is front-loaded with the core purpose and then systematically covers return states, batch behavior, and costing. Bold formatting for 'finished', 'pending', and 'failed' improves readability. Nothing is redundant or wasted.

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

Completeness5/5

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

With no output schema and no annotations, the description must fully inform the user about the tool's behavior, return values, and side effects. It does so comprehensively: it explains the three possible outcomes, the structure of results, error handling, polling discipline, and the fact that it neither starts nor bills a new job. This is complete for a polling tool.

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

Parameters5/5

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

While the schema already covers the single 'jobs' parameter well (100% coverage), the description adds critical meaning: the handles must be the exact objects returned by a prior generation call, and passing the same handle is required to rejoin the job. It also clarifies that multiple handles can be passed for a batch. This goes beyond the schema's basic type description.

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 states the tool's purpose: retrieving long-running generation jobs that were submitted earlier and returned a pending job handle. It distinguishes it from generation tools by explicitly saying it only rejoins existing jobs and never starts a new one. The verb 'retrieve' plus the resource 'pending generation job' is specific and unambiguous.

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 explicitly instructs when to use this tool (when a generation returns a pending status), and gives a critical exclusion: never re-submit a pending job with the creating tool to avoid duplicate billing. It also tells the user to wait a short time before polling again, and that failed jobs should not be re-polled. This is clear, actionable guidance with explicit alternatives.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/SupercmoHQ/superCMO-skills'

If you have feedback or need assistance with the MCP directory API, please join our Discord server