Skip to main content
Glama

Retry plan check

wever_retry-plan-check
Read-only

Agent Recovery: submit a system’s retry behavior: the standing retry plan (whether it is written down, the most attempts, how attempts are spaced, the first and longest wait, how long retrying may go on, the failures never retried, what happens when retrying stops and who hears, and whether rate-limit waits are honored), optionally the calls that retry with whether each follows the plan, its own attempt limit and whether it charges, sends, books or writes, and the failures the system sees with whether retrying can fix each and whether it is retried. The signed report states the plan’s headline (attempts, spacing and stop point) and names no plan, no bound on attempts or time, a stop nobody hears of, every failure retrying cannot fix that is retried and every call retrying without limit outside the plan, then a plan set only in code, retries at once, growing waits with no jitter, no never-retry list, a stop only logged or told to no one named, rate-limit waits ignored, every call on its own terms and every state-changing call retried, with the fix for each. This reads the standing plan across calls: whether one retry of a specific payment or refund flow can charge twice is wever_retry-safety-check, whether a resumed or retried task repeats a message, order, record or booking is wever_duplicate-effect-check and where a handed-off task goes when its receiver fails is wever_handoff-failure-check. A summary sample is wever_retry-plan-sample on https://weverlabs.com/mcp-free. Verdict retries_blind, retry_plan_gaps, retry_plan_unverified or retry_plan_stated. POST /api/retry-plan-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-recovery-contract. Human page: https://weverlabs.com/agent-recovery/.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "wever_retry-plan-check"
  }
}

Input Schema

NameRequiredDescriptionDefault
planNo
callsNoCalls that retry, with any behavior of their own.
labelNoOptional name recorded in the report.
systemNoThe system that retries, such as the booking agent.
failuresNoFailures the system sees, with whether each is retried.

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, openWorld=false), it discloses that no network request, money movement, message, sharing, configuration change or external write occurs, plus the cost model (0.10 USDC on Base via x402 exact, 10 free signed-wallet calls per 30 days), the required X-Wever-Wallet-Proof binding to the exact arguments and route, and the Ed25519-signed receipt return. The verdict taxonomy is also given, so the agent knows the result shape.

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, but the middle is one sprawling sentence that lists roughly a dozen finding categories and then repeats the parameter inventory, and the closing packs payment, auth, contract and page links together. Every element is relevant, yet the run-on phrasing makes it harder to scan than it needs to be.

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 stating what the signed report contains (headline attempts/spacing/stop point, named gap findings, per-item fixes) and by listing the four verdict values. Auth, pricing, side-effect profile and sibling routing are all covered, so nothing an agent needs in order to call it correctly is missing.

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 already 80%, and the description essentially re-enumerates the same plan, call and failure fields rather than adding interpretation. It does not explain how fields interact, such as how spacing values relate to delay/max_delay or when to supply per-call overrides versus the plan. Baseline 3 is appropriate when the schema carries the semantics.

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 system's retry behavior — the standing retry plan, optional per-call retry behavior and observed failures — and receive a signed report. It explicitly distinguishes itself from retry-safety-check, duplicate-effect-check and handoff-failure-check, so an agent can identify the tool without opening the schema.

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

Usage Guidelines5/5

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

It routes the agent explicitly: per-flow double-charge questions go to wever_retry-safety-check, repeated message/order/record/booking effects go to wever_duplicate-effect-check, and receiver-failure hand-off questions go to wever_handoff-failure-check. It also points at a free sample tool, making the when-to-use boundary concrete rather than inferred.

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