Decant: convert CSV, XLSX and PDF to JSON; web page extraction that honours robots.txt

Describe a need to Decant in words

interpret_requirement

Give Decant the buyer's requirement, or a correction or addition to it, in their own words: it is read into a structured requirement (each value says which words it came from), conflicting or unclear facts come back as one question, and words not yet read are kept as written. Pass the requirement (id, token) from the first answer to continue it. Nothing is sent or ordered: send_requirement sends it when the buyer says so. When you already have the fields in structured form, use submit_request instead.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "slug": "<slug>",
      "utterance": "<utterance>"
    },
    "name": "interpret_requirement"
  }
}

Input Schema

Name	Required	Description
`slug`	Yes	The service, from list_propositions
`turn_id`	No	Your id for this message: a retry with the same id is applied once
`timezone`	No	The buyer's IANA time zone, for reading dates
`utterance`	Yes	The buyer's words, as written
`requirement`	No	The requirement to continue

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations only declare readOnly=false, destructive=false, idempotent=false; the description adds real behavioral context — provenance of each value, conflicts collapsing into a single question, unread text preserved verbatim, and that nothing is sent or ordered. It does not mention retry/idempotency handling, though the schema's turn_id covers that.

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?

One front-loaded block with no filler: the core action, then output behavior, then the non-sending guarantee, then the alternative tool. Sentences are long and comma-heavy, which slightly hurts scanability, but every clause carries 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 five-parameter nested-object tool with no output schema, the description covers input intent, continuation mechanics, the shape of the response (structured values with source words, one clarifying question), and the safety boundary that nothing is dispatched.

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 baseline is 3; the description adds meaning by explaining that the requirement id and token are carried forward 'from the first answer to continue it' and that the utterance should be the buyer's own words, which clarifies intent beyond field-level docs.

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 and resource ('Give Decant the buyer's requirement... read into a structured requirement') and names the two dominant alternatives (send_requirement, submit_request), so the agent can distinguish it from siblings without inspecting schemas.

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 routing rules: use this to continue an existing requirement by passing its id and token, use send_requirement when the buyer authorizes dispatch, and use submit_request when fields are already structured. Both conditions and alternatives are spelled out.

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

All Decant: convert CSV, XLSX and PDF to JSON; web page extraction that honours robots.txt tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?