Skip to main content
Glama

Observability access check

wever_observability-access-check
Read-only

Agent Observability: submit who can see an agent’s traces and logs: each agent with the principal it works for; each grant with who holds it, their role (the principal, the operator, the agent, an auditor, a vendor, a third party or support), the agents it covers (* for every agent), what it shows (traces, logs or both) and the contract, consent or policy behind it; and optionally stored trace and log excerpts to read for secrets. The signed report lists for each agent what its principal sees and which outside parties see it, and every secret found by kind and position without its value, and names exposure and blindness: principals who cannot see their own agent’s records, third parties and other principals who can with no stated basis, and secrets or credentials written into traces and logs (private keys, API keys, cloud and chat tokens, bearer tokens, signed web tokens and labeled passwords); then a principal who sees traces or logs only, outside parties with a stated basis and grants naming agents not in the list, with the fix for each. Whether stored memories are shared beyond their principal is wever_memory-sharing-check and whether a read-only scope holds is wever_read-only-scope-check. Verdict exposed_or_blind, access_gaps, access_unverified or access_sound. POST /api/observability-access-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": {
      "agents": "<agents>"
    },
    "name": "wever_observability-access-check"
  }
}

Input Schema

NameRequiredDescriptionDefault
labelNoOptional name recorded in the report.
agentsYesEach agent with the principal it works for.
grantsNoEach grant of access to traces and logs.
samplesNoStored trace and log excerpts to read for secrets.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the annotations it discloses facts the structured fields cannot: it reads only material in the call with no network request, fetch, or external write; it is paid at 0.10 USDC per call on Base via x402 with 10 free signed-wallet calls per rolling 30 days; and X-Wever-Wallet-Proof must be bound to the exact JSON arguments and route. It also states return behavior — an Ed25519 signed receipt plus a report enumerating secrets by kind and position without values — which is substantial for a mutation-free but paid tool.

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 correctly in the first clause, but the rest is a single dense run of clauses that enumerates report contents, exposure categories, secret kinds, verdicts, pricing, auth binding, and links in one breath. The secret-kind list (private keys, API keys, cloud and chat tokens, bearer tokens, signed web tokens, labeled passwords) and the repeated restatement of the grant fields are the clearest places where words do not earn their place.

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 four parameters at full schema coverage, safety annotations, and no output schema, the description carries the return-value burden well — it describes the report structure, the secret redaction rule, the verdict set, and the receipt. The remaining hole is that no verdict is defined, so an agent knows the shape of the answer but not how to read it.

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 100%, so the baseline applies. The description's parameter-level text (roles enumerated, '* for every agent', traces/logs/both, basis, samples read for secrets) largely restates the schema's own field descriptions and never mentions the optional `label` parameter, so it adds little beyond structured data.

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 opening clause states a specific verb and resource: submit who can see an agent's traces and logs, and the report scope (per-agent visibility, external parties, secrets found). It then explicitly fences off two siblings by their subject matter (wever_memory-sharing-check for shared memories, wever_read-only-scope-check for read-only scope), so an agent can pick the right tool without opening another 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 makes clear the input is a declared access model plus optional samples, and names two adjacent checks with the condition that selects them. The gaps are the verdict semantics — exposed_or_blind vs access_gaps vs access_unverified vs access_sound are listed but never explained, so an agent cannot predict which outcome it will get.

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