Caliper

LAS/LAZ Analysis

format_las

Read-onlyIdempotent

Extract metadata from a LAS or LAZ point cloud file.

Returns LAS version, point format, point count, scale factors,
offsets, bounding box, classification counts, feature flags
(RGB, intensity, GPS time, waveform), and VLR information.

Payment via x402 (USDC on Base) or card via MPP (Stripe). See format_auto
for payment flow details. Privacy policy: https://caliper.fit/privacy

Input Schema

TableJSON Schema

Name	Required	Description
`payment`	No	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).
`file_b64`	No	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).
`file_url`	No	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).
`filename`	No	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.

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already provide readOnlyHint=true, idempotentHint=true, and openWorldHint=true. The description adds value by disclosing the specific return fields (point count, scale factors, offsets, bounding box, etc.) and payment methods (x402 and MPP). It does not contradict annotations and offers contextual detail beyond the structured hints, though it omits potential failure modes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three short sentences/paragraphs: purpose first, then the return payload, then payment/privacy. Every sentence carries essential information with no redundancy or filler. It is front-loaded and easy to scan.

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?

The tool has no output schema, so the description needs to convey what the agent can expect back. It lists the metadata fields comprehensively. It also explains payment prerequisites and points to a sibling for flow details. Some might argue for more depth on output structure, but given the moderate complexity and effective use of annotations, the description is sufficiently complete.

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% — all four parameters (payment, file_b64, file_url, filename) have detailed descriptions in the input schema. The tool description itself adds no parameter-specific information, so the baseline of 3 applies. The schema already explains semantics thoroughly.

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 uses a specific verb 'Extract metadata' and a precise resource 'LAS or LAZ point cloud file', making it immediately clear what the tool does. It also enumerates the exact metadata returned (LAS version, point format, etc.), which distinguishes it from other format_* sibling tools.

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 first sentence clearly tells the agent when to use this tool (for LAS/LAZ point cloud files), which implicitly separates it from siblings handling other formats. However, it does not explicitly name alternatives or state exclusions, and the reference to format_auto is only for payment flow, not for selecting an analysis tool. So it is clear but not 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 tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation5/5

Every tool has a clearly distinct purpose with no ambiguity. The general-purpose format_auto and format_batch tools cover multiple formats, while the format-specific tools (format_gltf, format_las, etc.) target individual formats, and feature_request serves a completely different administrative function. The descriptions clearly differentiate between auto-detection, batch processing, format detection, and format-specific analysis.

Naming Consistency5/5

All tools follow a consistent snake_case naming pattern with clear verb_noun structure. The format_ prefix is used consistently for 9 out of 10 tools (format_auto, format_batch, format_detect, format_gltf, etc.), while feature_request follows the same naming convention for the remaining tool. There are no deviations in naming style or convention.

Tool Count5/5

With 10 tools, this is well-scoped for a geometry file analysis server. Each tool earns its place by covering different aspects of the domain: general analysis (format_auto), batch processing (format_batch), format detection (format_detect), format-specific analysis (7 tools for different formats), and feature requests (feature_request). The count is neither too sparse nor overwhelming for the domain.

Completeness4/5

The tool surface provides excellent coverage for geometry file metadata extraction across multiple formats, with both general and format-specific tools. The inclusion of batch processing and format detection adds useful workflow support. The only minor gap is the lack of tools for actual mesh manipulation, repair, or conversion operations, but the server's stated purpose appears focused on analysis rather than modification, and feature_request allows users to request missing capabilities.

Resources

Need Help?