save_correctionsSave corrected field values for an extracted document. The original extraction is kept alongside the corrections; corrected data takes precedence in get_document, exports and reconciliation. Pass the complete corrected fields object (same shape as returned by get_document).
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Document id | |
| fields | Yes | Complete corrected fields object, including doc_type |
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?
Adds valuable behavioral context beyond annotations: original extraction is kept alongside corrections, and corrected data takes precedence. The requirement to pass the complete object implies a non-merge behavior. These align with idempotentHint and destructiveHint=false while providing richer semantics.
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?
Three sentences, each carrying essential information: action, behavioral effect, and required input format. No filler or redundant wording. Front-loaded with the purpose in the first sentence.
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?
Given the tool's simplicity (two params, no output schema), the description covers what, how, and side effects. It references get_document for shape, making it self-contained. Sibling differentiation is implicit and sufficient.
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 already documents both parameters clearly with 100% coverage. The description adds cross-reference to get_document for the shape of the fields object, which is useful beyond the schema. Reinforces the 'complete' requirement, though it repeats schema wording.
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?
Clear verb 'Save' plus resource 'corrected field values for an extracted document' precisely defines the action. It distinguishes from siblings like get_document, extract_batch, and export_documents by focusing on corrections. Mentioning precedence over originals further clarifies the tool's role.
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?
Explicitly instructs to pass the complete corrected fields object matching get_document's shape, providing concrete usage guidance. It explains when this tool matters by noting corrected data takes precedence in get_document, exports, and reconciliation. Does not explicitly state when not to use it, but context is clear.
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 targets a distinct action and resource: single extraction, batch extraction, document retrieval, listing, export, corrections, reconciliation, and account usage. extract_bol vs extract_batch is the only close pair, but single vs batch is a clear distinction.
All tool names follow a consistent verb_noun pattern with lowercase and underscores: export_documents, extract_batch, extract_bol, get_document, get_related_documents, get_usage, list_documents, save_corrections. No mixed styles or vague verbs.
8 tools is well within the ideal 3-15 range. Each tool earns its place by covering a distinct step in the document processing workflow, with no redundancy or bloat.
The toolkit covers the full lifecycle: extraction (single and batch), retrieval (get/list), update (save_corrections), export, reconciliation, and account management. There are no obvious gaps that would hinder agent workflows.