Skip to main content
Glama

Create document from PDF upload

create-document-from-pdf-upload

Create a new document from a PDF previously uploaded via create-document-pdf-upload-url.

Use this tool when:

  • The user wants to import an existing PDF into fynk as a draft document for further processing, OR

  • The user wants to record an already-signed PDF in fynk by setting initial_stage to "done"

Call create-document-pdf-upload-url first to obtain file_upload_uuid, then upload the PDF to the URL it returns with a multipart/form-data POST, as that tool describes, before calling this tool. initial_stage is required and must be either "draft" or "done"; ask the user which they want if it isn't clear from context. Depending on the account's settings, template_uuid may be required (it copies checkpoints, document type, metadata, parties, etc. from a template).

Only pass auto_apply_ai_analysis when the user has expressed whether AI analysis results should be applied to the document automatically; omit it to use the account's default setting.

The team_uuids, tag_uuids, and account_party_uuid arguments expect UUIDs, which can be discovered via list-account-teams, list-account-tags, and list-account-parties respectively.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
file_nameYesThe name of the file being uploaded
tag_uuidsNoUUIDs of the tags to apply to the document. UUIDs can be obtained from list-account-tags
team_uuidsNoUUIDs of the teams to assign the document to. May be required depending on the account's settings. UUIDs can be obtained from list-account-teams
document_nameNoThe name of the new document. If omitted, the file_name will be used. Ask the user if they would like to give their own name for the document
initial_stageYesThe new document will be created in this stage. Prompt the user for this if they don't supply it
template_uuidNoUUID of the template to copy Checkpoints, document type, metadata, parties, etc from. If present, must be one of the template UUIDs returned by list-templates. May be required depending on the account's settings.
file_upload_uuidYesUUID given by create-document-pdf-upload-url
account_party_uuidNoOptional UUID of the account party to add to the document as the internal party. UUID can be obtained from list-account-parties
auto_apply_ai_analysisNoIf true, results of the AI analysis of the document (metadata, parties, etc.) are applied to the document automatically instead of being left for manual review. If not sent, the account's auto_apply_ai_analysis_by_default setting from get-account-info is used.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNoURL to open the document in fynk
nameNoName of the document
tagsNoThe tags on the document. Tags are the account's own classification labels (e.g. relationship type, commercial significance, region), so they show which categories this account uses and can be filtered on with filter_tags.
uuidNoUnique identifier for the document. Do not show to the user unless they ask for it
stageNoWhat stage the document is in currently
teamsNoThe teams the document is assigned to.
localeNoLocale code, e.g. en-GB, de-AT. Absent when the document has none set. Prefer describing the locale in natural language (e.g. 'British English') rather than showing the raw code.
originNoHow the document was created.
partiesNoThe contracting entities on the document.
conditionsNoThe document's conditions: rules over its dynamic fields deciding whether a passage of the document applies, and whether each currently holds. Use them to explain why a clause is or is not part of the document, and what would have to change to flip it.
created_atNoWhen the document was created.
updated_atNoWhen the document was last updated.
archived_atNoWhen the document was archived. Absent when the document is not archived.
signatoriesNoThe individual people who sign the document. Distinct from parties: a signatory often signs on behalf of a party (e.g. a business), so a person may be a signatory without appearing as a party.
_entity_typeNoOnly relevant for tooling. Do not show to the user
summary_textNoA summary of the document content. Absent when the document has no summary.
document_typeNoIf present, indicates what kind of document this is. Absent when the document has no type assigned
dynamic_fieldsNoThe document's dynamic fields and their values.
signature_typeNoeIDAS assurance level used when signing the document. Absent when none has been chosen.
workflow_stateNoGives an indication of which stage transitions, etc are possible to perform on this document. This object is technical state, not display content: when relaying it to the user, always render it as natural-language prose and never echo raw field names or snake_case values (e.g. say 'signing cannot be started yet because not every signature block has been assigned to a signatory' instead of mentioning 'can_start_signing' or 'signature_block_signatory').
metadata_valuesNoThe document's metadata fields and their values.
signature_blocksNoThe places in the document that are signed. A block is bound either to a single signatory or to a party, in which case every signatory of that party signs it. Every signatory needs a block covering them before signing can be started.
sequential_signingNoWhen true, signatories sign one at a time, in ascending order of their signing_order.
source_template_uuidNoUUID of the template the document was created from. Absent when it was not created from a template.
external_signatory_invitation_messageNoText shown in the email inviting external signatories to sign. Absent when no message is set.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations establish this is a non-read, non-destructive create. The description adds real context beyond that: the two-step prerequisite workflow, that template_uuid may be required per account settings, that auto_apply_ai_analysis falls back to an account default from get-account-info, and that initial_stage must be prompted from the user. It stops short of describing side effects or the resulting document state.

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?

Purpose is front-loaded, followed by a bulleted when-to-use block and then the prerequisite/parameter guidance. The longer length is justified by the 9-parameter workflow, and each sentence carries actionable information.

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 9-parameter creation tool with an output schema (so returns need not be explained), the description covers purpose, when to use it, prerequisites, conditional requirements, and defaults. Nothing an agent needs to invoke it correctly is missing.

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%, so each parameter is already documented, and the description mostly restates that (UUID discovery via list-account-teams/tags/parties, initial_stage values, auto_apply_ai_analysis default). It adds the workflow framing around file_upload_uuid but little semantic detail the schema lacks, so baseline 3 is appropriate.

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 states a specific verb (Create) and resource (a new document) and identifies the source as a PDF previously uploaded, immediately distinguishing it from create-document-from-scratch and create-document-from-template. The two usage bullets further sharpen what the tool is for.

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?

It gives explicit when-to-use conditions (import an existing PDF as a draft, or record an already-signed PDF by setting initial_stage to "done") and names the prerequisite tool create-document-pdf-upload-url with the ordering and upload step required before this call. Conditional requirements for template_uuid and auto_apply_ai_analysis are also flagged.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources