Skip to main content
Glama

query_image

Answer free-form questions about any image using visual QA. Use it to read watermarks, logos, or stylized text, and get consistency checks that flag low-confidence or contradictory AI answers.

Instructions

Ask a free-form question about an image (visual question answering).

This is the right tool for reading photo watermarks, logos, signage, or any cursive/stylized/low-contrast text — ask e.g. "What does the text/watermark say, exactly?". The ocr tool misreads that kind of text confidently; prefer this one for it instead.

Moondream2 is a small model and is documented to answer open-ended judgment questions ("describe anything wrong in this image") with a flat "None" on images that all had real visible defects, and to give the same yes/no answer across genuinely different images -- a default response, not a real observation. Set check_consistency=true to make that visible: the tool also asks a rephrased control question and returns, per image, {answer, control_answer, consistent, confidence}. confidence is "low" in either of two failure modes: the two answers agree on a short default-looking token ("None", "Yes", "Nothing", ...), which is the signature of a flat default rather than a genuine observation; or they substantively contradict each other, which makes either answer weaker evidence than it looks alone. "normal" requires substantive answers that agree. A low result on a judgment question means you should not trust the answer without independent confirmation. When the answer is low-confidence, the tool also tries to route to the measurement that actually answers the question: it classifies the question's wording and, if a measurable category applies and the object names parse from the wording, runs that tool's measurement (spatial_relations for a contact/containment question, count_objects for "how many", ocr for a text-reading question, detect_objects for "which is largest/smallest") and attaches it as cross_check. The "largest/smallest" case detects every instance of the named object and picks the extremum by bounding-box area, returning its box -- so "which circle is biggest" resolves to coordinates, not a repeated guess. The cross-check is omitted when no measurement applies or the names can't be parsed -- it never guesses.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
srcYesLocal file path or http(s) URL of the image to process. PDFs are also accepted and are rendered one image per page, so tools that return a list return one entry per page.
questionYesA free-form question to ask about the image.
check_consistencyNoWhen true, also ask a rephrased control question and report whether the two answers agree. `confidence` is 'low' in two cases: the answers agree on a short default-looking token ('None', 'Yes', 'No', 'Nothing', ...), or they substantively contradict each other. Moondream2 is a small VLM that answers open-ended judgment questions ('describe anything wrong') with a flat 'None' on images that all had real visible defects -- this layer makes that default-answer behavior visible instead of presenting it as reliable. On a low-confidence answer it also routes to the measurement that actually answers the question when one applies (spatial_relations for a contact/containment question, count_objects for 'how many', ocr for a text-reading question) and attaches it as `cross_check`. Default false keeps the original list[str] return; true returns one {answer, control_answer, consistent, confidence, cross_check?} dict per image.
structured_analysisNoWhen true, bypasses the simple VQA return and returns structured Observation and Anomaly payloads per image. Corroborates VLM claims against physical Grounding DINO measurements to proactively detect anatomical and structural AI generation artifacts (e.g. extra/missing body parts).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / check_consistency / description
      Previous value: -"When true, also ask a rephrased control question and report whether the two answers agree, flagging short default-looking answers ('None', 'Yes', 'No', 'Nothing', ...) as low confidence. Moondream2 is a small VLM that answers open-ended judgment questions ('describe anything wrong') with a flat 'None' on images that all had real visible defects -- this layer makes that default-answer behavior visible instead of presenting it as reliable. On a low-confidence answer it also routes to the measurement that actually answers the question when one applies (spatial_relations for a contact/containment question, count_objects for 'how many', ocr for a text-reading question) and attaches it as `cross_check`. Default false keeps the original list[str] return; true returns one {answer, control_answer, consistent, confidence, cross_check?} dict per image."New value: +"When true, also ask a rephrased control question and report whether the two answers agree. `confidence` is 'low' in two cases: the answers agree on a short default-looking token ('None', 'Yes', 'No', 'Nothing', ...), or they substantively contradict each other. Moondream2 is a small VLM that answers open-ended judgment questions ('describe anything wrong') with a flat 'None' on images that all had real visible defects -- this layer makes that default-answer behavior visible instead of presenting it as reliable. On a low-confidence answer it also routes to the measurement that actually answers the question when one applies (spatial_relations for a contact/containment question, count_objects for 'how many', ocr for a text-reading question) and attaches it as `cross_check`. Default false keeps the original list[str] return; true returns one {answer, control_answer, consistent, confidence, cross_check?} dict per image."
  2. First observedv0.8.2

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so thoroughly. It discloses the model's documented failure modes (flat 'None' answers, same yes/no across different images), explains the confidence semantics, and describes the cross-check routing behavior including when it is omitted ('it never guesses'). This is exactly the kind of behavioral context an agent needs beyond the schema.

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 long but every sentence earns its place: it covers purpose, sibling differentiation, failure modes, confidence semantics, and cross-check routing. It is front-loaded with the core purpose and the key alternative. It loses one point for density — the cross-check explanation is somewhat run-on and could be tightened — but it is not padded or redundant.

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?

Given the tool's complexity (4 params, no annotations, rich behavioral nuances, output schema present), the description is complete. It explains the return types, the failure modes, the confidence field, the cross-check routing, and the structured_analysis bypass. An agent has everything needed to decide when to call it and how to interpret results.

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 meaningful value beyond the schema by explaining the return-shape change when check_consistency=true (list[str] vs dict per image) and by detailing the cross-check routing logic that depends on the question wording. It also clarifies the src parameter's PDF behavior indirectly through the schema, but the description's main added value is on check_consistency semantics, which are already partially in the schema. The description does not add much beyond the schema for src or question, but the check_consistency elaboration justifies a 4.

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 opens with a specific verb and resource ('Ask a free-form question about an image (visual question answering)') and immediately distinguishes itself from the ocr sibling by naming the exact use case (watermarks, logos, signage, stylized text). It clearly identifies what the tool does and what it is not for, so an agent can select it correctly without opening the schema.

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?

The description explicitly says when to prefer this tool over ocr ('The ocr tool misreads that kind of text confidently; prefer this one for it instead'), and it gives concrete example questions. It also explains when to set check_consistency=true and when the cross-check routing applies, providing clear decision guidance for the agent.

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