Skip to main content
Glama

MCPFax Agent Continuity

by com.mcpscores
OverviewDiscussionsAdmin

Leave a note for your future self

inbox_schedule

Leave work for your own next invocation — the same as send() addressed to yourself. FREE. No callback URL is required or accepted: agents are not web services and mostly have no endpoint, so the model is a future inbox, not a webhook. Whenever your next invocation starts, inbox_poll finds this waiting. FREE — this tool never charges. Authenticate with Authorization: Bearer , or pass agent_key as an argument if your host cannot set headers. Equivalent HTTP route: POST /v1/inbox/schedule.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
boxNoSub-mailbox name, default 'inbox'. Example: 'inbox'.
scopeNoOptional unit of work this task belongs to, so resume_packet groups it. Example: 'permit-review-2026-08'.
due_atNoISO-8601 due time. Example: '2026-08-13T09:00:00Z'.
contextNoOpaque payload. Never parsed or logged. Example: '{"permit_id":"P-1"}'.
historyNoPrior reasoning or tool output. Example: '[]'.
priorityNo0 (highest) to 9. Default 5. Among DUE items, delivery order is priority first, then oldest due time. Example: '5'.
agent_keyNoYour agent_secret, if your MCP host cannot set the Authorization header. Prefer the header.
objectiveYesWhat future-you should achieve, <=2048 chars. Example: 'Re-check the permit status'.
dedupe_keyNoOptional duplicate suppression key. Example: 'permit-P-1'.
in_secondsNoAlternative to due_at: seconds from now. Example: '3600'.
attachmentsNoOpaque refs or blobs. Example: '[]'.
repeat_countNoFurther occurrences to queue. Default 0, max 1000. Example: '7'.
every_secondsNoOptional repeat interval (>=60). Example: '86400'.
max_deliveriesNoAttempts before dead-lettering. Default 5, max 50. Example: '5'.
provider_extrasNoVendor/framework-specific state. Carried verbatim, never interpreted. Example: '{}'.

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. Changed14 schema fields changed
    • addedInput schema / properties / attachments / examples
      Added value: +[
+  "[]"
+]
    • addedInput schema / properties / box / examples
      Added value: +[
+  "inbox"
+]
    • addedInput schema / properties / context / examples
      Added value: +[
+  "{\"permit_id\":\"P-1\"}"
+]
    • addedInput schema / properties / dedupe_key / examples
      Added value: +[
+  "permit-P-1"
+]
    • addedInput schema / properties / due_at / examples
      Added value: +[
+  "2026-08-13T09:00:00Z"
+]
    • addedInput schema / properties / every_seconds / examples
      Added value: +[
+  86400
+]
    • addedInput schema / properties / history / examples
      Added value: +[
+  "[]"
+]
    • addedInput schema / properties / in_seconds / examples
      Added value: +[
+  3600
+]
    • addedInput schema / properties / max_deliveries / examples
      Added value: +[
+  5
+]
    • addedInput schema / properties / objective / examples
      Added value: +[
+  "Re-check the permit status"
+]
    • addedInput schema / properties / priority / examples
      Added value: +[
+  5
+]
    • addedInput schema / properties / provider_extras / examples
      Added value: +[
+  "{}"
+]
    • addedInput schema / properties / repeat_count / examples
      Added value: +[
+  7
+]
    • addedInput schema / properties / scope / examples
      Added value: +[
+  "permit-review-2026-08"
+]
  3. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations are all false and therefore provide no behavioral safety or idempotency signals. The description adds substantial context: the tool is free, never charges, accepts no callback URL, delivers via inbox_poll on next invocation, and supports two auth methods. This exceeds what the annotations give, though it leaves side effects like dedupe or repeat semantics to the schema.

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

Conciseness4/5

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

Four sentences that front-load the core purpose and then cover cost, delivery, and auth in a compact way. The word FREE appears twice, a minor redundancy, but the overall description is tight and doesn't waste sentences on fluff.

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?

For a tool with 15 parameters and no output schema, the description provides the necessary orientation: what to schedule, how it gets delivered, how to authenticate, and the pricing implication. Itdoesn't cover return values or error cases, but those aren't expected given the absence of an output schema and the schema's own param documentation.

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?

The schema already covers 100% of parameters with descriptions and examples, so the baseline is 3. The description only mentions agent_key as an alternate auth mechanism, which is a small addition already reflected in the schema. It adds no new meaning for objective, due_at, in_seconds, repeat_count, or other fields.

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 verb and resource: leave work for your own next invocation. It explicitly compares itself to send() addressed to yourself, which distinguishes it from the sibling send tool and clarifies its self-addressed scheduling purpose. The metaphor in the title reinforces the concept without replacing a functional definition.

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 clearly frames the intended scenario: scheduling work for your own future invocation, with inbox_poll as the retrieval mechanism. It explains why no callback URL is involved, effectively contrasting with webhook-style delivery and implying when this tool is appropriate. It doesn't enumerate exclusion cases or alternatives beyond send(), but the context is sufficiently clear.

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