easydeploy-ai-mcp

Official

Overview Schema Source Related Servers Discussions Admin

Complete upload

complete_upload

Finalize a validated upload as a dataset after its session reaches READY, creating a new dataset or adding a new version to an existing one.

Instructions

upload_request_id: opaque id returned by start_upload. dataset_id: omit it to create a new dataset named name. Pass an existing dataset's id (the one given to start_upload) to add a new version to that dataset; name is then still required but ignored, and the dataset keeps its current name. dataset_type: train | test | validation (default train). You produce these files by splitting the prepared data yourself: train is what the model learns from, test is the holdout you score afterwards with run_batch_prediction, and validation is an optional extra holdout. EasyDeploy stores the type as a label and never splits for you.

The upload session must be in status READY — not UPLOADED. READY means the validator has accepted and promoted the bytes. RECEIVING / UPLOADED / VALIDATING (still in flight), REJECTED (failed validation) and EXPIRED (needs a new start_upload) return 400 naming the current state and what to do. Call get_upload_status first and wait for READY instead of calling this tool on a guess.

Retrying is safe: if the session is already CONSUMED (an earlier call succeeded), the API returns the existing dataset version instead of an error. A 409 means another complete_upload for the same session is still in progress — wait a few seconds and call again.

A file the user uploaded through the web model builder is already a dataset — resolve it with list_datasets rather than calling this.

Returns dataset (id, name, ui_url) and datasetVersion once, at the top level, with its ui_url and columnNames as a list.

qa_status is informational and does not gate anything. version_type matters in one case: submit_training_job with an explicit dataset_version_id rejects a raw version. Omit dataset_version_id to train on the model version's own dataset.

Input Schema

TableJSON Schema

Name	Required	Default
`name`	Yes
`dataset_id`	No
`project_id`	Yes
`description`	No
`dataset_type`	No	train
`upload_request_id`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.3.0Oct 2, 2026
- addedInput schema / properties / dataset_type / enum
```
Added value: +[
+  "train",
+  "test",
+  "validation"
+]
```
First observedv0.1.0May 29, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly=false, destructive=false, openWorld=false), yet the description adds substantial behavioral context: the session state machine, which states return 400 and why, what 409 means, and that a CONSUMED session returns the existing version. The only friction is that this retry-safety statement reads as idempotent behavior while the annotation sets idempotentHint=false; the annotation is best read as a conservative default here, and the description mutes rather than contradicts the mutation semantics.

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?

Front-loaded with the core action and then organized by parameter, then by state requirements, then by error handling — dense but every paragraph carries operational information. It is long, and the closing paragraph on qa_status/version_type is only loosely tied to this tool's own behavior, so slight trimming was possible.

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?

For a mutation tool that ends an upload session, the description covers prerequisites, retry behavior, failure modes, and routing alternatives; the output schema exists so return values need no further explanation, and the brief mention of what is returned is harmless. Nothing an agent needs 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?

Schema description coverage is 0%, so the description must carry all parameter meaning, and it does for the important ones: upload_request_id (opaque id from start_upload), dataset_id (omit to create new, pass existing to add a version, name then required but ignored), and dataset_type (train/test/validation with default and semantics). It leaves project_id and description unexplained, so it compensates strongly but not completely.

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?

Names a specific verb and resource ('Register a validated upload as a dataset') and situates it in the workflow ('the last step of every channel'), which cleanly separates it from start_upload and get_upload_status. An agent can tell exactly what state transition this performs without consulting the 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 prerequisites (session must be READY, not UPLOADED, and instructs calling get_upload_status first rather than guessing), explicit exclusions (a file uploaded via the web model builder should be resolved with list_datasets instead), and retry/409 escalation guidance. This is a full when/when-not/alternative treatment against named siblings.

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