Skip to main content
Glama

Caliper

by fit.caliper
OverviewDiscussionsAdmin

Auto-Detect and Analyze

format_auto
Read-onlyIdempotent

Auto-detect geometry file format and extract metadata statistics.

Accepts a 3D geometry file via URL or base64 and returns structured
metadata: bounding boxes, triangle counts, manifold analysis, point
cloud statistics, and more. This is a read-only analysis tool — it
does not perform mesh repair, format conversion, or boolean operations.

Supported formats: STL, OBJ, PLY, PCD, LAS/LAZ, glTF/GLB.
STEP and IGES support is planned.

Provide either file_url (preferred for large files) or file_b64
(for files under 200KB). Include filename for format detection if
using file_b64. When using file_url, the format is detected from
the URL path extension; filename is not required.

Files under 150KB are free. Larger files cost $0.02/MB via x402
(USDC on Base) or card via MPP (Stripe; adds $0.35 surcharge).
If payment is required, the response includes payment details.
Retry with the payment argument containing the payment proof.
Privacy policy: https://caliper.fit/privacy

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
paymentNoPayment proof as a JSON string. Set this when retrying after a payment_required response. For x402: must contain 'transaction' (on-chain tx hash), 'network', and 'priceToken' from the payment_required response. For MPP: must contain 'challenge' and 'payload' from the org.paymentauth/credential flow. Default: null (omit on first call; set only when retrying with payment).
file_b64NoBase64-encoded file content. Max 200KB decoded. Use file_url for larger files to avoid consuming model context window budget. Default: null (omit if providing file_url instead).
file_urlNoHTTP/HTTPS URL of the geometry file to analyze. Preferred for large files (over 200KB). The file format is detected from the URL path extension, so the filename parameter is not needed when using file_url. Max 100MB. Default: null (omit if providing file_b64 instead).
filenameNoOriginal filename with extension (e.g. 'model.stl'). Required for format detection when using file_b64. Not needed when using file_url (format is detected from the URL path). Default: null.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / payment / description
      Previous value: -"x402 payment proof as a JSON string. Set this when retrying after a payment_required response. Must contain 'transaction' (on-chain tx hash), 'network', and 'priceToken' copied from the payment_required response. Example: {\"transaction\": \"0xabc...\", \"network\": \"base\", \"priceToken\": \"4:1776026505:1fe9...\"}. Default: null (omit on first call; set only when retrying with payment)."New value: +"Payment proof as a JSON string. Set this when retrying after a payment_required response. For x402: must contain 'transaction' (on-chain tx hash), 'network', and 'priceToken' from the payment_required response. For MPP: must contain 'challenge' and 'payload' from the org.paymentauth/credential flow. Default: null (omit on first call; set only when retrying with payment)."
  2. Changed4 schema fields changed
    • changedInput schema / properties / file_b64 / description
      Previous value: -"Base64-encoded file content. Use for files under 200 KB."New value: +"Base64-encoded file content. Max 200KB decoded. Use file_url for larger files to avoid consuming model context window budget. Default: null (omit if providing file_url instead)."
    • changedInput schema / properties / file_url / description
      Previous value: -"HTTP/HTTPS URL of the geometry file to analyze. Preferred for large files."New value: +"HTTP/HTTPS URL of the geometry file to analyze. Preferred for large files (over 200KB). The file format is detected from the URL path extension, so the filename parameter is not needed when using file_url. Max 100MB. Default: null (omit if providing file_b64 instead)."
    • changedInput schema / properties / filename / description
      Previous value: -"Original filename with extension, used for format detection when providing file_b64."New value: +"Original filename with extension (e.g. 'model.stl'). Required for format detection when using file_b64. Not needed when using file_url (format is detected from the URL path). Default: null."
    • changedInput schema / properties / payment / description
      Previous value: -"x402 payment proof as a JSON string. Set this when retrying after a payment_required response. Must contain 'transaction' (on-chain tx hash), 'network', and 'priceToken' from the payment_required details."New value: +"x402 payment proof as a JSON string. Set this when retrying after a payment_required response. Must contain 'transaction' (on-chain tx hash), 'network', and 'priceToken' copied from the payment_required response. Example: {\"transaction\": \"0xabc...\", \"network\": \"base\", \"priceToken\": \"4:1776026505:1fe9...\"}. Default: null (omit on first call; set only when retrying with payment)."
  3. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already mark the tool as readOnly, idempotent, and openWorld. The description adds substantial behavioral context: it returns metadata such as bounding boxes and triangle counts, has file size thresholds, may require payment for larger files, and requires retrying with payment proof. It also reiterates the read-only nature without contradicting the annotations.

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 longer than ideal, but each section (purpose, formats, input modes, pricing, payment) is relevant to invoking the tool correctly. Some phrases like 'STEP and IGES support is planned' and the privacy link are not directly actionable but are minor.

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?

Despite having no output schema, the description names the key returned metadata categories and explains input constraints, supported formats, and the payment/retry workflow. This is sufficient for an agent to select and invoke the tool correctly, especially with the sibling list providing format-specific alternatives.

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% and each parameter already has a detailed description. The description adds a high-level usage rule ('Provide either file_url ... or file_b64') and explains the payment retry flow, which adds meaning beyond the schema's per-field descriptions.

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 opening sentence 'Auto-detect geometry file format and extract metadata statistics' clearly states the tool's function. It also explicitly distinguishes itself from conversion/mesh-repair tools by stating it does not perform mesh repair, format conversion, or boolean operations, and it lists supported formats.

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?

The description gives clear context for when to use this tool (read-only analysis of geometry files) and states what it does not do (format conversion, boolean operations). However, it never explicitly names sibling tools like format_stl or format_batch as direct alternatives, so the 'vs alternatives' guidance is implicit rather than fully explicit.

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

All Caliper toolsInspect
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