Skip to main content
Glama

Observability retention check

wever_observability-retention-check
Read-only

Agent Observability: submit a trace and log retention policy: each rule with the records it covers (traces, logs, an audit log, metrics, alerts, payment records or other), the runs it applies to (all runs, successful runs or failed runs), how long they are kept (a period such as 90 days or 7 years, or forever), how they leave when the period ends (deleted automatically, deleted by hand or not deleted) and whether they move to an archive first with how long the archive keeps them; and the dispute, audit or contract windows the work is under, each with its period and the records it needs. The signed report gives each rule how long its records stay available, each window the rules it reads, and failed runs beside successful ones, and names records that disappear too soon: retention shorter than the dispute or audit window the work is under, deletion with no archive, and failed runs losing their records sooner than successful ones; then failed runs kept longer, a rule for successful runs with none for failed runs, a window needing records no rule covers and traces or logs not kept at all, with the fix for each. A counterparty’s data retention and deletion policy is wever_data-retention-check and an agent memory setup’s retention is wever_memory-retention-check. Verdict records_lost, retention_gaps, retention_unverified or retention_holds. POST /api/observability-retention-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-observability-contract. Human page: https://weverlabs.com/agent-observability/.

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": {
      "rows": "<rows>"
    },
    "name": "wever_observability-retention-check"
  }
}

Input Schema

NameRequiredDescriptionDefault
rowsYesEach retention rule for traces and logs.
labelNoOptional name recorded in the report.
obligationsNoEach dispute, audit or contract window the work is under.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations (readOnly, closed-world, non-destructive), the description discloses that the call reads only supplied material with no network fetch, external write or configuration change, and adds pricing (0.10 USDC via x402 exact, 10 signed-wallet free calls per rolling 30 days), the X-Wever-Wallet-Proof binding requirement, and that the result carries an Ed25519 signed receipt. That is substantial behavioral context an agent could not infer from the annotation block.

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 purpose is front-loaded and every clause carries information (rule fields, report contents, gap classes, verdicts, payment, auth binding), but the opening is one sprawling semicolon-chained sentence that is hard to parse. It is dense rather than padded, yet readability suffers and the verdict list is buried.

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?

There is no output schema, and the description compensates by enumerating what the signed report contains (per-rule availability, window-to-rule mapping, failed vs successful runs, each gap class and its fix) plus the verdict vocabulary. With pricing, auth binding, contract and human-page links included, an agent has everything needed to call and interpret the result.

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, but the description adds interaction semantics the schema does not: rules carry records/scope/duration/deletion/archive, while obligations are the dispute, audit or contract windows with their own periods and required records, and it clarifies that windows 'read' rules. It largely restates per-field meanings that the schema already documents thoroughly, hence 4 rather than 5.

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: submit a trace/log retention policy and receive a signed report naming records that disappear too soon. It also explicitly names the two nearest siblings, wever_data-retention-check (counterparty data policy) and wever_memory-retention-check (agent memory), so an agent can distinguish scope without opening a schema.

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?

It routes the agent away from the two closest alternatives by naming the domain each covers, which is real when-to-use guidance. It does not state explicit when-not conditions or prerequisites (e.g., minimum viable input), so it stops short of a full 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources