Skip to main content
Glama

MCPFax Agent Continuity

by com.mcpscores
OverviewDiscussionsAdmin

Attempt count and backoff that survives a crash

retry_state
Idempotent

Durable retry bookkeeping, so backoff survives the session that died. Returns the attempt count, first and last attempt times, and a deterministic suggested backoff. Pass record:true to count this attempt. $0.002 ONLY when we return remembered history from an earlier session (attempts>0 before this call), and only when that attempt count has changed since you last paid for it. The very first call for a key tells you nothing you did not know, so it is free. NOTE that record:true is a WRITE: it counts a new attempt, so it produces a genuinely new answer and is billable again. Use the default record:false to read the history without changing it. Costs $0.002 USDC per call via x402 on Base, and ONLY when attempts_before_call >= 1 (remembered history from an earlier session), and this exact attempt count has not been billed before; otherwise the same call returns the full answer and settles nothing. Authenticate with Authorization: Bearer , or pass agent_key as an argument if your host cannot set headers. Equivalent HTTP route: POST /v1/retry-state.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyYesWhat is being retried. Namespace-scoped, hashed before storage. Example: 'sync-vendor-7'.
scopeNoOptional unit of work, so resume_packet can report what is being retried. Example: 'permit-review-2026-08'.
recordNoCount this attempt before answering. Default false. Example: 'true'.
agent_keyNoYour agent_secret, if your MCP host cannot set the Authorization header. Prefer the header.
ttl_secondsNoRetention. Default 604800 (7d), max 2592000. Example: '604800'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / agent_key / examples
      Added value: +[
+  "the agent_secret that register returned"
+]
  2. Changed4 schema fields changed
    • addedInput schema / properties / key / examples
      Added value: +[
+  "sync-vendor-7"
+]
    • addedInput schema / properties / record / examples
      Added value: +[
+  "true"
+]
    • addedInput schema / properties / scope / examples
      Added value: +[
+  "permit-review-2026-08"
+]
    • addedInput schema / properties / ttl_seconds / examples
      Added value: +[
+  604800
+]
  3. First observed

TDQS

B3.4/5.0
Behavior1/5

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

The description is richly transparent about billing, auth, write behavior, and determinism, but it directly contradicts the idempotentHint:true annotation. It states that record:true counts a new attempt, produces a genuinely new answer, and is billable again, meaning repeated identical calls are not idempotent. Per rubric, a description that contradicts annotations scores 1.

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 purpose is front-loaded, but the billing conditions are explained twice in near-duplicate passages ('$0.002 ONLY when...' and 'Costs $0.002 USDC per call... ONLY when...'), adding meaningful bloat. A single consolidated billing statement would have been clearer and shorter.

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

Completeness3/5

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

The description covers return values, auth, HTTP route, read/write modes, TTL default, and billing despite having no output schema. However, the contradictory idempotency annotation leaves an agent unsure whether retrying a record:true call is safe, and the 'deterministic suggested backoff' is not detailed enough to fully compensate for the missing output schema.

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 100% with examples for all five parameters, so the baseline is 3. The description adds meaning beyond the schema by explaining that record:true is a WRITE with billing consequences, while record:false is a non-mutating read, and by linking scope to resume_packet reporting.

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 states a specific resource ('durable retry bookkeeping') and a clear purpose: return attempt count, first/last attempt times, and deterministic suggested backoff so retries survive a crash. This clearly distinguishes retry_state from the sibling checkpoint, barrier, heartbeat, and work-management tools.

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 gives clear context for when to use the tool: durable retry bookkeeping after a session dies. It also instructs when to pass record:true (count this attempt) versus the default record:false (read history without changing it). It does not explicitly name sibling alternatives or when-not-to-use conditions, so it misses full alternative guidance.

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

All MCPFax Agent Continuity 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