DeepMark

Get Ingestion Job State

ingestion_get

Read-onlyIdempotent

Read the current state of an ingestion job (paper creation or document ingestion). Returns the status plus a derived awaiting gate ('triage' | 'confirmation' | null), whether it is terminal, and the next action to take. Poll this after starting a job: a paper-creation job parks at awaiting_confirmation (then call paper_confirm) — it does NOT run to complete on its own. Stop polling on a terminal status (complete | failed | cancelled) or when an action is required.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`job_id`	Yes	ID of the ingestion job to read the current state of.

Output Schema

TableJSON Schema

Name	Required	Description
`kind`	Yes	The ingestion job kind (paper_bundle, student_batch, source_document, …).
`error`	Yes	Failure detail, when status is failed.
`job_id`	Yes
`status`	Yes	Raw ingestion status.
`awaiting`	Yes	The gate the job is parked at, or null if none.
`terminal`	Yes	True once the job will not change on its own.
`created_at`	Yes	ISO-8601 creation timestamp.
`needs_action`	Yes	Human-readable next step for the caller.
`processed_at`	Yes	ISO-8601 completion timestamp, or null if not yet processed.
`attempt_count`	Yes	Processing attempts so far.
`exam_paper_id`	Yes	The minted paper's id, once one exists.
`triage_summary`	Yes	Triage explanation, only while parked at the triage gate.
`triage_issue_count`	Yes	How many triage issues, only while parked at the triage gate.

TDQS

A4.7/5.0

Behavior5/5

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

The description goes well beyond the readOnlyHint and idempotentHint annotations by disclosing derived state (awaiting gate), the parking behavior of paper-creation jobs, and terminal statuses. It also tells the caller when to stop polling, which is critical operational context not present in annotations. No contradictions with annotations.

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 four sentences, front-loaded with purpose and return values, then usage instructions. Every sentence adds unique value: purpose, return contents, polling guidance, and termination criteria. No fluff or repetition of schema/annotations.

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?

Given the tool's moderate complexity (state machine, polling, cross-tool action), the description covers the full usage lifecycle: when to call, what to expect, when to stop, and what to do next. The presence of an output schema handles return format details, so the description is complete for the agent's invocation decision.

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% for the single parameter job_id, so the schema fully documents it. The description adds no additional parameter semantics beyond reaffirming that this is a polling operation. Baseline 3 is appropriate as the schema carries the burden.

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 verb 'Read' and the resource 'current state of an ingestion job', distinguishing it from sibling getters like paper_get and submission_get by scoping to ingestion jobs. It also specifies the returned fields (status, awaiting gate, terminal, next action), making the tool's purpose 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?

Explicitly says 'Poll this after starting a job' and provides concrete stopping conditions (terminal status or when action is required). It also names the next action for paper-creation jobs (call paper_confirm) and warns that such jobs do not run to complete on their own. This is clear when/where-to-use guidance, including an alternative (paper_confirm) for the follow-up step.

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

All DeepMark tools Inspect

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

A4/5.0

Disambiguation4/5

The tools map well to distinct resources and workflow stages, and the async flows are clearly explained. The main overlap risk is paper_create/paper_confirm and markResult_get/submission_get, where names point at similar actions but the descriptions make the boundaries usable.

Naming Consistency4/5

Most names follow the same resource_action snake_case pattern, e.g. paper_get, submission_mark, markScheme_update. markResult_get breaks the pattern slightly by mixing camelCase into an otherwise snake_case set, but the naming stays readable and predictable overall.

Tool Count5/5

Ten tools is a well-scoped size for this domain: paper creation, confirmation, retrieval, question/mark-scheme correction, and submission grading are covered without excess granularity or obvious filler.

Completeness4/5

The main end-to-end workflow—create extraction job, confirm paper, mark submission, poll results—is complete and coherent. Minor gaps exist, such as no paper deletion, no submission listing, and no direct way to fetch a mark scheme separately, but they are not blocking for the core grading loop.

Resources

Need Help?