Skip to main content
Glama

Check a photo location claim

verify_location_claim

Test whether an image is consistent with a location someone has already claimed: a listing's stated city, an address on a case file or claim form, a caption. Oceanir locates the image from visual evidence alone FIRST, then compares. Returns a verdict of agrees, contradicts, or unverifiable, with the distance between the claim and the evidence. unverifiable means the image does not settle it and the item needs a human. It is a real answer, not a failure. A verdict of agrees means the image is consistent with the claim, not that the claim is true. Reads the scene only (architecture, signage, terrain, vegetation), never the people in it. No face recognition, no biometric identification, no person matching. It answers where an image was taken, never who is in it, and must not be used to locate or track a person.

Input Schema

NameRequiredDescriptionDefault
depthNoAnalysis depth. 2 = Standard is the right default for verification; 1 = Surface is city-level only and will rarely contradict anything; 3 = Forensic adds contradiction checks (10 credits).
scopeYesThe location being claimed. Oceanir treats this as a search boundary and never as evidence: it can only narrow the search, never raise confidence, and the model will reject it outright on hard image-legible contradiction (signage in an impossible script, the wrong driving side, a landmark that is elsewhere).
image_b64NoBase64-encoded image bytes (no data: prefix).
image_urlNoPublic HTTPS URL to the image to test.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Goes well past annotations (readOnlyHint=false, openWorldHint=true) by disclosing the return verdict set, the meaning of each verdict, the distance output, the explicit caveat that `agrees` proves consistency not truth, and the privacy boundary (scene only, no faces/biometrics, never for tracking people). These are exactly the behavioral traits an agent needs before calling an open-world, credit-consuming analysis.

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 verdict behavior and the scoping caveat are front-loaded and high value. The closing privacy sentences are somewhat repetitive ('never the people', 'no face recognition, no biometric identification, no person matching', 'never who is in it') and could be tightened.

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?

No output schema exists, so the description takes on the burden of explaining return values and does so fully (verdict enum, distance, unverifiable semantics). Combined with the privacy scope and the pre-explained search-boundary behavior of `scope`, an agent has everything needed to call and interpret this correctly.

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% and the schema itself richly documents `depth`, `scope`, `radius_km`, and `captured_at` semantics. The description adds no parameter-level detail beyond that, so the 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 ('test whether an image is consistent with a location someone has already claimed') and clarifies the two-stage internal behavior (locate first, then compare). It implicitly distinguishes itself from geolocate_image by framing itself as verification against an existing claim.

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 concrete usage contexts (listing's stated city, case file address, caption) and explains that `unverifiable` means a human is needed, which is a decision rule for the agent. It does not explicitly say 'use geolocate_image instead when no claim exists', leaving that inference to the agent, so it falls short of a 5.

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.