Share by DeltaBreen

create_id_check

Ask a person to confirm who they are: an ID check by Didit (a photo of their passport, ID card, driving licence or residence permit and a live selfie), and if asked a sanctions and PEP check and a proof of address. Emails them the link from the human's account. Counts against the plan's ID checks this month. Returns only the check's id, status and the page where the human sees the result; you never see the person's details.

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": {
      "email": "<email>"
    },
    "name": "create_id_check"
  }
}

Input Schema

Name	Required	Description
`email`	Yes	The person's email address. The invitation goes there, from the human's account.
`address`	No	Also ask for a recent proof of address (a utility bill or a bank statement).
`message`	No	A short note for the invitation, in the human's words.
`keep_copy`	No	Keep a copy of the ID and selfie, locked to the workspace, for the firm's records.
`sanctions`	No	Also check their name against sanctions lists and lists of politically exposed people.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 30, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Goes well beyond the annotations: it discloses that the link is emailed from the human's account, that the call consumes the plan's monthly ID-check quota, and that the tool returns only the check id, status and result page with no access to the person's details. These are exactly the cost and privacy traits an agent needs before invoking a non-idempotent, open-world mutation.

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?

A single dense paragraph that front-loads the core purpose, then layers optional checks, cost, and return behavior in a sensible order. Every clause carries information, though the long compound sentences could be split for faster scanning.

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?

With no output schema, the description usefully explains what comes back (id, status, result page) and covers cost, privacy, and document scope. It is nearly complete; only timing/asynchrony (e.g., how the check completes and when to use get_id_check or remind_id_check) is left implicit.

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 coverage is 100%, so each parameter already carries its own description. The description reinforces the email mechanism ('Emails them the link from the human's account') and mentions the sanctions/address options in prose, but adds little syntax or meaning beyond the schema. Baseline 3 applies.

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?

States a specific verb and resource: 'Ask a person to confirm who they are: an ID check by Didit', naming the document types collected and the optional checks. An agent can immediately tell this is the creation tool for an ID verification request, distinct from get_id_check and list_id_checks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description conveys the scenario (inviting a person to verify their identity) and implies when the address/sanctions options should be added, but never names an alternative or states when not to use this tool versus, say, prepare_signature_request. Usage is implied rather than explicitly guided.

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

All Share by DeltaBreen 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?