Skip to main content
Glama
Sign In

Skavio PDF, OCR & Document Processing MCP

by io.github.skavio-eu
OverviewDiscussionsAdmin

skavio_get_job

Read-onlyIdempotent

Fetch one processing job owned by the authenticated company using an id from skavio_submit_job or skavio_list_jobs. Poll queued/processing jobs until completed or failed; returns id, operation, status, stage, estimated_credits, charged_credits, error and result metadata. Also updates this adapter's local accounting for the observed job; it never resubmits work or creates another charge. On completion use result.files[].id with skavio_download_result; the response contains metadata rather than file bytes. Use skavio_list_jobs to find an unknown ID or skavio_reconcile to refresh multiple tracked jobs. Unknown or foreign IDs fail without exposing other tenants.

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": {
      "job_id": "<job_id>"
    },
    "name": "skavio_get_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
job_idYesID of a job owned by the authenticated company, copied from skavio_submit_job.id or skavio_list_jobs.jobs[].id. Preserve it exactly; foreign or unknown IDs fail. For downloads the job must be completed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / description
      Added value: +"Arguments for skavio_cancel_job. Company and permissions come from the authenticated connection."
    • addedInput schema / properties / job_id / description
      Added value: +"ID of a job owned by the authenticated company, copied from skavio_submit_job.id or skavio_list_jobs.jobs[].id. Preserve it exactly; foreign or unknown IDs fail. For downloads the job must be completed."
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations declare a safe read (readOnlyHint, idempotent, non-destructive), and the description still adds real behavioral context: it updates the adapter's local accounting but 'never resubmits work or creates another charge', returns metadata rather than file bytes, and foreign IDs 'fail without exposing other tenants'. Those are exactly the non-obvious traits an agent cannot infer from the schema.

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 core action and scope lead, followed by polling behavior, side-effects, and the download hand-off, then alternatives last. Sentences are dense but each carries distinct information — no restatement of the tool name or filler.

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?

There is no output schema, and the description compensates by enumerating the returned fields (id, operation, status, stage, estimated_credits, charged_credits, error, result) and warning that files come via download_result, not bytes. Combined with the failure-mode note for unknown IDs, nothing needed to call this correctly is missing.

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

Parameters4/5

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

With 100% schema coverage the single job_id parameter is already documented with pattern and constraints, so the baseline would be 3. The description adds provenance (which sibling produced the ID) and reinforces the exact-match requirement, but offers no format or edge-case detail the schema lacks.

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 ('Fetch one processing job') scoped to 'owned by the authenticated company', and ties the identifier to skavio_submit_job / skavio_list_jobs. An agent can distinguish this from list_jobs, cancel_job and reconcile without opening any schema.

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?

Gives explicit when-to-use ('poll queued/processing jobs until completed or failed'), explicit alternatives ('Use skavio_list_jobs to find an unknown ID or skavio_reconcile to refresh multiple tracked jobs'), and a downstream step ('On completion use result.files[].id with skavio_download_result'). The condition that rules each alternative in is stated, not implied.

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

All Skavio PDF, OCR & Document Processing MCP toolsInspect
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