Skip to main content
Glama

Memory export check

wever_memory-export-check
Read-only

Agent Memory: submit an export flow: how the principal gets an export (on their own, by asking, or not at all), its format (JSON, CSV, Markdown, plain text, HTML, PDF, a proprietary format only the agent reads, or another), the categories it covers, whether it includes the agent’s inferences marked as inferences and each item’s source, and how long it takes, plus optionally every category kept about the principal, what the export withholds with the reason and whether the principal is told, the stated time an export should take and the export requests seen with when each arrived and whether it was complete. The signed report says whether the principal can obtain everything remembered about them, in a readable form, inferences included, and whether anything is withheld, and names no export, a format only the agent reads, inferences left out, every category kept but silently missing from the export, everything withheld without telling the principal and every export delivered incomplete, then an export only on request, items without their source, every category withheld with the principal told, an export slower than the stated time and every request delivered late, with the fix for each. This reads whether the principal can take their memory with them: export claims checked against a provider’s terms are wever_export-evidence-check, whether an agent’s own identity works outside its platform is wever_identity-portability-check and whether a removal request clears memory everywhere is wever_memory-deletion-check. Verdict memory_locked, export_gaps, export_unverified or principal_can_take_it. POST /api/memory-export-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-memory-contract. Human page: https://weverlabs.com/agent-memory/.

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": {
      "export": "<export>"
    },
    "name": "wever_memory-export-check"
  }
}

Input Schema

NameRequiredDescriptionDefault
flowNoThe export flow, such as download my data.
heldNoEvery category kept about the principal, to compare with what the export covers.
labelNoOptional name recorded in the report.
exportYes
targetNoHow soon an export should arrive, such as 7 days.
requestsNoExport requests seen, with when each arrived.
withheldNoWhat the export leaves out.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior5/5

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

Beyond the read-only/open-world annotations, it discloses the full cost and access model (0.10 USDC per call on Base via x402 exact, 10 signed-wallet free calls per rolling 30 days), the authentication requirement (X-Wever-Wallet-Proof bound to the exact JSON arguments and tool route), the read-only scope in concrete terms, and the return artifact (report with Ed25519 signed receipt). These are exactly the auth, rate-limit and side-effect facts annotations cannot carry.

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?

The content is relevant but delivered as a handful of 80-150 word run-on clauses that pile every failure mode, verdict name and infrastructure detail into single sentences. Payment, endpoint, contract link, verdicts and sibling routing all compete for attention, and the most decision-relevant line (what the tool decides) is buried mid-paragraph rather than 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 and seven parameters including a nested object, the description does the needed work: it states the verdict vocabulary (memory_locked, export_gaps, export_unverified, principal_can_take_it), the return shape (report plus signed receipt), the HTTP route and the contract reference. The only gap is that the verdict names are listed but not individually defined, leaving mild ambiguity about which verdict a borderline input yields.

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 already 86%, so the baseline is 3, but the description adds comparative semantics the schema does not: 'held' is meant to be compared against what the export 'covers' to surface 'every category kept but silently missing', and 'withheld' entries are judged on both the reason given and whether the principal is told. It also glosses the format enum ('a proprietary format only the agent reads') and that inferences must be 'marked as inferences', which clarifies intent.

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 names a specific verb and resource ('submit an export flow', 'reads whether the principal can take their memory with them') and enumerates exactly which claims are checked: availability, format readability, category coverage, inference marking, sourcing, withholding, latency and completeness. It explicitly separates itself from wever_export-evidence-check, wever_identity-portability-check and wever_memory-deletion-check, so an agent can place it among siblings without opening any 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 names three concrete alternatives and states the condition each covers ('export claims checked against a provider's terms are wever_export-evidence-check', 'whether an agent's own identity works outside its platform is wever_identity-portability-check', deletion is wever_memory-deletion-check). That is strong alternative-routing, but there is no explicit statement of when this check should be skipped or what input is insufficient to run it.

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