Wever Labs Agentic Rails

Knowledge freshness check

wever_knowledge-freshness-check

Read-only

Agent Knowledge: submit knowledge entries with their dates and the moment to read them at: each entry with its id, its claim, its topic, its kind (a price, a version, an officeholder, a rate, a schedule, contact details, a policy, a statistic, a definition, history or other), the date its fact was true or published, when it was last checked against its source, its review or expiry date and whether the knowledge base serves it as current or as historical; and optionally how old an entry on a fast-moving topic may be and still be served as current (90 days when left out). The signed report gives every entry its age at the reading moment, its kind as stated or as read from the words of its topic and claim, and its status, and names entries served as current that are not: entries past their review date, entries with no date at all, and prices, versions, officeholders and other fast-moving topics carried on entries older than the age limit; then entries served as current with no review date, entries dated after the reading moment and entries that record a review with no date for the fact itself, with the fix for each. Entries marked historical are read as history and never as stale. Which earlier answers a named policy or source change makes stale is wever_answer-freshness-check, how long a cached element can outlive its source is wever_cache-staleness-check and how long a stored memory is kept is wever_memory-retention-check. Verdict stale_as_current, currency_gaps, currency_unverified or entries_current. POST /api/knowledge-freshness-check. Reads only the material in the call: no network request, fetch, money movement, message, sharing, configuration change or external write. Paid URL: 0.10 USDC per call on Base via x402 exact, with the shared 10 signed-wallet free calls per rolling 30 days. Bind X-Wever-Wallet-Proof to the exact JSON arguments and the tool route. Returns a report with an Ed25519 signed receipt. Contract: /api/agent-knowledge-contract. Human page: https://weverlabs.com/agent-knowledge/.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "entries": "<entries>",
      "as_of": "<as_of>"
    },
    "name": "wever_knowledge-freshness-check"
  }
}

Input Schema

Name	Required	Description
`as_of`	Yes	The moment to read the entries at, such as 2026-11-15.
`label`	No	Optional name recorded in the report.
`entries`	Yes	Each knowledge entry.
`fast_max_age`	No	How old an entry on a fast-moving topic may be and still be served as current, such as 90 days; 90 days when left out.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 10, 2026

TDQS

A4/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, but the description goes well beyond them: it states the tool reads only the material in the call with no network request or external write, discloses the paid x402 pricing (0.10 USDC on Base, 10 signed-wallet free calls per rolling 30 days), the required X-Wever-Wallet-Proof binding to the exact JSON arguments, and that the response carries an Ed25519 signed receipt. It also enumerates the verdict outcomes (stale_as_current, currency_gaps, currency_unverified, entries_current), which is exactly the behavioral context an agent needs before paying for a call.

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

Conciseness3/5

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

The operational payload (verdicts, endpoint, pricing, auth binding, receipt) is valuable, but the opening half is a semicolon-chained re-listing of the input schema's fields that duplicates the 100%-covered schema and delays the point. It is one unbroken block with no paragraphing, so the routing information an agent most needs sits at the end rather than being front-loaded.

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?

With no output schema, the description carries the burden of describing returns, and it does: entry age at the reading moment, resolved kind, status, the current-but-not-actually-current categories, and the four verdict labels. What is left unspecified is the concrete report shape (field names, ordering, receipt placement), which stops just short of fully complete for a report-emitting tool.

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 coverage is 100%, so the schema already documents every parameter including the kind enum, the presented_as default of current and the 90-day default for fast_max_age. The description restates those defaults rather than adding new meaning, such as date-format tolerance, how fast_max_age interacts with kind, or what happens when review_by and reviewed_at conflict.

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?

The description makes clear that the tool takes knowledge entries plus a reading moment and returns a signed freshness report, and it explicitly separates itself from the answer, cache and memory freshness siblings. The core verb is buried under a long enumeration of entry fields in the opening clause, so an agent must read well into the text before the actual operation ('the signed report gives every entry its age...') is clear.

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?

Three named alternatives are given with the scope each covers (answer freshness, cache staleness, memory retention), and there is an explicit exclusion rule: entries marked historical are never read as stale. What is missing is a plain 'use this when you need to verify that knowledge entries served as current are still current' framing up front; the routing is inferable from the closing sentences rather than stated as a use case.

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

All Wever Labs Agentic Rails 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?