form fill-mcp

list_form_fields

Inspect a PDF and return every fillable field: name, type, current value, and x/y position on the page.

ALWAYS call this before fill_form. Use the exact field names returned here — never guess.
Use the position coordinates (x, y) to identify what each field represents visually:
higher y = higher on the page in PDF coordinates. Fields with similar y values are on
the same horizontal line; fields with similar x values are in the same column.
The response also includes pdf_type so you know if the PDF may have rendering quirks.

Input Schema

TableJSON Schema

Name	Required	Description
`api_key`	No	Your FormFill API key (get one at formfill.plenitudo.ai).
`pdf_path`	Yes	Absolute path to the PDF file on disk.
`payment_proof`	No	x402 payment proof (tx hash). Alternative to api_key for pay-per-use.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

TDQS

A4.5/5.0

Behavior4/5

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

No annotations are provided, so the description carries the burden. It discloses that the tool reads a PDF and returns fields, including position coordinates and pdf_type, which helps the agent anticipate output. However, it doesn't detail failure modes (e.g., password-protected PDFs) or whether the tool modifies anything, but the read-only nature is implied by 'Inspect'.

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?

The description is well-structured: a clear first sentence, then imperative guidance, and explanatory notes. It is slightly long but every sentence adds value (precondition, coordinate interpretation, pdf_type caveat). Not as tight as two sentences, but justified.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has an output schema and rich description that covers purpose, usage, coordinate interpretation, and pdf_type. It lacks explicit preconditions like 'PDF must exist' or error handling, but given the output schema and the guidance provided, it is sufficiently complete for an inspection tool. Sibling tools and the 'ALWAYS call before fill_form' instruction provide good context.

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 coverage is 100%, so the schema already documents pdf_path, api_key, and payment_proof. The description adds context by explaining how to use the returned coordinates but doesn't add much beyond schema for parameters. Baseline 3 is elevated to 4 because the description ties the output to the tool's purpose and gives practical usage hints for the parameters.

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 clearly states the tool inspects a PDF and returns every fillable field with name, type, current value, and position. It distinguishes itself from siblings like fill_form by emphasizing this is the inspection/predecessor step. The verb 'Inspect' and specific resource 'fillable field' make the purpose unambiguous.

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?

Explicitly instructs to 'ALWAYS call this before fill_form' and provides guidance on using coordinates to interpret field positions. It also mentions pdf_type for handling rendering quirks. This gives clear when-to-use context and differentiates from fill_form and extract_form_data.

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

All form fill-mcp tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.3/5.0

Disambiguation4/5

Tools are mostly distinct: list_form_fields and extract_form_data read form structure/values, fill_form and fill_form_multipage handle filling with clear usage boundaries, and flatten_form finalizes. The two fill tools share purpose but are explicitly differentiated by document length and complexity.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case: extract_form_data, fill_form, fill_form_multipage, flatten_form, list_form_fields. The naming clearly indicates the action and target, with no mixed conventions.

Tool Count5/5

Five tools cover the essential PDF form workflow (inspect, read, fill, flatten) without redundancy. The count is well-scoped for the server's purpose.

Completeness5/5

The tool surface covers the full lifecycle of working with PDF forms: listing fields, extracting data, filling single- or multi-page forms, and flattening. No critical operations are missing for common form-filling scenarios.

Resources

Need Help?