WellState Labs SB 1150 Screening (read-only)

Verify publication hashes

verify_publication

Read-onlyIdempotent

Recomputes the publication root hash from the manifest copy bundled with this server, reports the SHA-256 and byte count of each manifest data file as verified against the manifest when the server was built (all files, or the given paths), and re-hashes every bundled derived index file against its build attestation. Also returns the manifest URL and file URL template for an independent check, and the manifest's Full Wellbore cross-check counts when the edition carries them.

Input Schema

Name	Required	Description	Default
`paths`	No	Manifest data_files paths to report (e.g. data/operator.ndjson). Omit to report every file.

Output Schema

Name	Required	Description	Default
`root`	Yes
`files`	Yes
`terms`	Yes
`derived`	Yes
`boundary`	Yes
`all_match`	Yes
`elapsed_ms`	Yes
`files_checked`	Yes
`files_matched`	Yes
`publication_root`	Yes
`independent_check`	Yes
`full_wellbore_crosscheck`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 30, 2026

addedOutput schema / properties / terms

Added value: +{
+  "const": "https://mcp.wellstatelabs.com/terms",
+  "type": "string"
+}

changedOutput schema / required

Previous value: -[
-  "boundary",
-  "publication_root",
-  "root",
-  "files",
-  "files_checked",
-  "files_matched",
-  "derived",
-  "full_wellbore_crosscheck",
-  "all_match",
-  "elapsed_ms",
-  "independent_check"
-]New value: +[
+  "boundary",
+  "terms",
+  "publication_root",
+  "root",
+  "files",
+  "files_checked",
+  "files_matched",
+  "derived",
+  "full_wellbore_crosscheck",
+  "all_match",
+  "elapsed_ms",
+  "independent_check"
+]

First observedOct 30, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, and the description adds genuinely new context: verification is against the manifest copy bundled at build time, not a live remote, and it exposes manifest/file URLs so the caller can independently check. It stops short of saying what happens on a hash mismatch (error vs. reported discrepancy).

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 core purpose is front-loaded in the opening clause and every subsequent clause carries real information (data files, index files, URLs, cross-check counts). It is a single very dense sentence, though, and would read better split into two or three.

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?

Return content is well sketched (SHA-256 and byte counts, re-hash of index files, manifest URL, file URL template, cross-check counts) and an output schema exists to carry the structure. The one missing piece is failure semantics – whether a mismatch throws or is returned as data.

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?

The description notes 'all files, or the given paths', which matches the schema's own 'Omit to report every file' text, so the semantics of the optional array are confirmed rather than added. With 100% schema description coverage the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Precise verbs (recomputes, reports, re-hashes) paired with specific resources (publication root hash, manifest data files, derived index files) make the integrity-verification role unambiguous. It is clearly distinct from sibling get_publication, though that sibling is never explicitly named as the contrasting read path.

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

Usage Guidelines3/5

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

Use is only implied by the word 'verify' – an agent can infer this is for integrity checking rather than data retrieval. There is no explicit statement of when to call it instead of get_publication, and no preconditions or cost guidance.

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

All WellState Labs SB 1150 Screening (read-only) tools Inspect

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

Need Help?