Skip to main content
Glama

AIDNode | AI Agent Support Network

repair

AIDNode Repair v2: classify HTTP/transport failures, retry safety, idempotency, Retry-After, bounded backoff. Advisory only.

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": {
      "operation_id": "<operation_id>"
    },
    "name": "repair"
  }
}

Input Schema

NameRequiredDescriptionDefault
methodNo
statusNo
attemptNo
max_attemptsNo
operation_idYesUnique call id 8-100 characters; counted once by beta ledger
network_errorNo
response_headersNo
retry_after_secondsNo
idempotency_key_presentNo
request_may_have_committedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / network_error / enum
      Added value: +[
      +  "ECONNRESET",
      +  "ETIMEDOUT",
      +  "ECONNREFUSED",
      +  "EAI_AGAIN",
      +  "DNS_ERROR",
      +  "NETWORK_ERROR",
      +  "TLS_ERROR"
      +]
  2. First observed

TDQS

C2.6/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden. "Advisory only" is genuinely useful — it tells the agent this call has no side effects and will not itself retry or mutate state — but the description never says what the advisory output looks like (a decision, a delay, a boolean), nor that inputs are purely descriptive of an already-failed request.

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?

It is a single short sentence with no filler, which is good, but the "AIDNode Repair v2" prefix spends the front-loaded position on a name already in the tool name. The keyword-list structure is dense but low-information; each term is named without being explained.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter tool with nested objects, two enums, no annotations, and no output schema, this description is far too thin. The agent cannot tell what the return value is, how the flags combine, or what "bounded backoff" is bounded by, so it must guess at the tool's decision model.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 10 parameters at 10% schema coverage, only operation_id is documented and the description must compensate, which it largely does not. The phrases "Retry-After", "idempotency", and "bounded backoff" hint at retry_after_seconds, idempotency_key_present, and max_attempts/attempt, but method, status, network_error, response_headers, and especially request_may_have_committed — the most consequential flag — get no explanation of how they change the classification.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Classify HTTP/transport failures, retry safety, idempotency, Retry-After, bounded backoff" conveys the domain and the verb (classify), so an agent knows it produces a judgment rather than performing the retry. However it is a keyword list rather than a stated purpose, and it gives no basis for distinguishing it from the sibling "recovery" tool, whose name suggests overlapping retry logic.

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

Usage Guidelines2/5

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

"Advisory only" is the sole usage signal, and it is a constraint on behavior rather than a when-to-use rule. There is no statement of when an agent should call repair instead of recovery, verify, or monitor, and no preconditions (e.g. must a failure have already occurred?).

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.