mindee_get_inferenceFetch the structured result of a completed inference by id, returned as a compact map of extracted fields (plus raw_text if it was requested). V2 API: GET /v2/inferences/{inference_id}.
| Name | Required | Description | Default |
|---|---|---|---|
| raw | No | Return the full unshaped API response instead of the compact fields map. Default false. | |
| inference_id | Yes | Inference id (from a Processed job's result_url, or from mindee_extract_document). |
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?
Annotations already declare readOnlyHint=true, and the description adds value by specifying the return format as a 'compact map of extracted fields (plus raw_text if it was requested)'. This goes beyond the annotation's safety indication, providing useful output expectations. No contradiction exists.
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 with the main action front-loaded, followed by a concise output description and API endpoint. Every sentence provides necessary information without fluff.
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?
For a simple retrieval tool with 2 parameters, the description covers the action, output shape, and endpoint. It does not explain error handling or pagination, but these are not critical given the tool's simplicity and the presence of annotations. The return format detail adds completeness.
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?
Schema coverage is 100% with both parameters described (inference_id and raw). The description mentions 'by id' which aligns with the inference_id parameter but does not add significant new semantics beyond the schema. The mention of raw_text in the output is not directly a parameter detail.
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 tool fetches the structured result of a completed inference by ID, using specific verbs ('Fetch') and a specific resource ('structured result of a completed inference'). It distinguishes itself from siblings like mindee_get_job (job status) and mindee_extract_document (submission) by focusing on the result retrieval.
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 usage after an inference is completed ('completed inference'), giving clear context on when to call it. It does not explicitly mention alternatives or when not to use it, but the purpose is distinct enough from sibling tools to guide selection.
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 has a clearly distinct purpose: extracting documents, fetching inference results, checking job status, and listing available models. There is no overlap or ambiguity between them.
All tool names follow a consistent pattern: the 'mindee_' prefix followed by verb_noun (extract_document, get_inference, get_job, list_models). This makes the set predictable and easy to navigate.
With only 4 tools, the server is tightly scoped to the essential Mindee operations: submit, poll, retrieve, and explore models. Each tool earns its place, and the count is ideal for this purpose.
The tool set covers the full document extraction lifecycle: listing models, enqueuing extraction (with built-in polling), checking job status for long-running requests, and fetching the final inference result. No critical operation is missing.