Skip to main content
Glama

Check a selfie against an ID or photo

face_verify

Compare a selfie with an ID document or face photo, detect spoofing, and check document authenticity to support identity verification decisions.

Instructions

Check that a selfie shows the same person as an ID document or face photo, and that the selfie is a genuine capture (not a printout, screen, mask or synthetic face), via Face Terminal (POST /v1/face/verify). When the reference is a passport, ID card, residence permit or driving licence, the document is checked too. Takes local file paths (JPEG, PNG or WebP, up to 12 MB each). Returns status (verified, review or failed), reasons, the face match, the spoof check and the document check. Uses one check from the key's quota. You need a lawful basis, usually the person's explicit consent, to send their face. A result supports a human decision.

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": {
      "reference": "<reference>",
      "selfie": "<selfie>"
    },
    "name": "face_verify"
  }
}

Input Schema

NameRequiredDescriptionDefault
backNoPath to the back of the ID card or driving licence in reference (optional)
fullNoReturn the whole API response instead of a summary
selfieYesPath to a selfie of the person, taken now
referenceYesPath to the ID document page or a clear face photo to match against

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses the spoof-detection scope, accepted formats and per-file size cap, quota consumption ('one check from the key's quota'), consent requirements, the three possible statuses and the components of the result. It also warns against treating output as an automated decision.

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?

Dense but front-loaded: purpose, then document scope, then input constraints, then returns, cost, and legal caveat. Nearly every sentence adds a distinct operational fact, though the block would scan faster as short segments rather than one long paragraph.

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 4-parameter, annotation-free tool with no output schema, the description covers purpose, inputs, constraints, return fields, billing impact and legal caveats. An agent has everything needed to decide whether to call it and how to interpret the response.

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, but the description adds real meaning on top: it specifies accepted formats (JPEG, PNG, WebP) and a 12 MB limit per file, and clarifies via the document types that the optional `back` image applies to ID cards and licences. The `full` parameter is only covered by the schema, not extended further.

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?

Opens with a specific verb and dual resource ('Check that a selfie shows the same person as an ID document or face photo') and adds the liveness/spoof dimension, so the agent knows exactly what the tool decides. The endpoint reference (POST /v1/face/verify) and named inputs make it unambiguous.

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

Usage Guidelines4/5

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

Gives clear framing for when this applies: comparing a selfie to a reference document or photo, with doc verification included when the reference is a passport/ID/residence permit/licence. It adds a legal precondition (lawful basis, usually explicit consent) and the caveat that results support a human decision, but gives no explicit when-not-to-use or alternative path, since no siblings exist.

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

Deploy Server

Other Tools