Skip to main content
Glama
Sign In

Wever Labs Agent Products

by io.github.CodeWever
OverviewDiscussionsAdmin

Partial state check

wever_partial-state-check
Read-only

Agent Recovery: submit a task system’s state reporting: whether it has a state for partly done work apart from done and failed, whether a partly done task lists the pieces that did not complete, what lets a task be reported done (every part confirmed, the last step returning, no error raised or any response) and what it reports when a task fails partway (partly done, failed, done, still in progress or nothing), plus optionally the tasks it reported on after a mid-task failure with each piece, whether it finished and the pieces the report named as missing. The signed report says whether partial completion is visible and labeled as partial with its missing pieces named, and names a system that reports done on a mid-task failure, on any response or on no error, or reports nothing, and every task reported done with unfinished pieces (half-done work presenting as finished), then no partial state, done on the last step alone, a partial failure shown as failed or still running, missing pieces left unnamed and every task reported failed with finished pieces, with the fix for each. This reads what an interrupted task’s reported state shows across a system: one paid call’s delivered result against its order is wever_result-validation-check, what a stop does to in-flight actions is wever_kill-switch-check and where an interrupted task picks up is wever_resume-point-check. Verdict half_done_looks_done, partial_state_gaps, partial_state_unverified or partial_shown_as_partial. POST /api/partial-state-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/.

Input Schema

NameRequiredDescriptionDefault
labelNoOptional name recorded in the report.
tasksNoTasks the system reported on after a mid-task failure, with their pieces.
systemNoThe task system, such as the booking pipeline.
reportingYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

Beyond the readOnly/non-openWorld annotations, it discloses materially useful behavior: a flat 0.10 USDC paid call on Base via x402 exact, 10 signed-wallet free calls per rolling 30 days, an X-Wever-Wallet-Proof header that must be bound to the exact JSON arguments and route, and an Ed25519 signed receipt in the response. It also enumerates the four possible verdicts and reaffirms the no-side-effect scope (no fetch, money movement, message, sharing, config change or external write). The main gap is that the auth/payment prose is buried in the wall of text rather than called out, and nothing is said about behavior on malformed or over-limit input (1000 tasks / 100 parts).

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

Conciseness2/5

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

One enormous run-on paragraph packs the purpose, field enumeration, verdict list, sibling routing, payment terms, auth binding, contract link and human page into near-unreadable chains ('...or any response) and what it reports when a task fails partway (partly done, failed, done, still in progress or nothing), plus optionally...'). The operational essentials (price, wallet proof, verdicts) are not front-loaded or separated, so an agent must scan the whole block. Little is individually redundant, but the structure actively harms comprehension.

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?

For a nested-object, no-output-schema tool this covers what an agent needs: which fields drive the verdict, what the report asserts, the four verdict outcomes, the signed-receipt return, cost/auth mechanics, and links to the contract and human page. Return values needn't be enumerated precisely because the receipt/verdict behavior is described and no output schema is claimed.

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 75%, so the schema already carries most parameter meaning, and the description largely restates it — enumerating the same reporting fields (partial state, missing pieces named, done_when values, mid-task failure outcome) and the tasks/parts/missing_named structure. It adds modest value by framing these fields as the inputs to the judgment and by hinting that tasks may be omitted or left empty, but it introduces no new constraints, formats, or defaults beyond the schema. Baseline 3 is appropriate.

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 opening clause names a specific action and object — submitting a task system's reported state to check whether partial completion exists and is visible. It also explicitly separates itself from three named siblings (wever_result-validation-check, wever_kill-switch-check, wever_resume-point-check) by question type. It loses a point only because the purpose must be reconstructed from a very dense, comma-chained sentence rather than stated in one clean line.

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 description routes the agent away from adjacent tools with concrete conditions: delivered result vs. order → result-validation, effect of a stop on in-flight actions → kill-switch, resume location → resume-point. It also implies when to use it (an interrupted/mid-task failure with reported states). What it lacks is an explicit exclusion such as when a partial-state check is not the right call at all (e.g., no mid-task interruption occurred).

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

All Wever Labs Agent Products toolsInspect
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