Cito API

webhook_deliveries

Read-only

A webhook's delivery log, newest first: event, status (delivered, failed, skipped_backoff), HTTP code, error and a diagnosis. Pass deliveryId for one delivery with its payload. skipped_backoff means the event was NOT sent because the webhook was paused; see catch_up_webhook. API calls: 1.

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": {
      "id": "<id>"
    },
    "name": "webhook_deliveries"
  }
}

Input Schema

Name	Required	Description
`id`	Yes	The webhook id, from list_webhooks or create_webhook. Never invent one.
`event`	No	Only this event name.
`limit`	No	Max items to return (default 20, max 100). Example: 20.
`since`	No	ISO 8601 time.
`until`	No	ISO 8601 time.
`cursor`	No	nextCursor from the previous page.
`status`	No	delivered, failed, skipped_backoff; comma separated.
`matchId`	No	Only this match.
`summary`	No	Add 7-day counts by status.
`deliveryId`	No	One delivery, with its payload.

Output Schema

Name	Required	Description
`ok`	Yes	true if the tool succeeded
`data`	No	Result payload when ok is true; null on error
`meta`	Yes
`error`	No
`partial`	No
`pagination`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 8, 2026

TDQS

A4/5.0

Behavior4/5

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

With readOnlyHint/destructiveHint already covering safety, the description adds genuine behavioral context: result ordering (newest first), the meaning of skipped_backoff (event was NOT sent because the webhook was paused), and cost ('API calls: 1'). It omits pagination behavior beyond the cursor param and any retention/lookback window, which keeps it below a 5.

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?

It is compact and front-loads the resource and ordering before the deliveryId special case and the skipped_backoff caveat. Sentences are dense but each carries information; the 'API calls: 1.' tail is terse but useful for cost planning.

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 10-parameter tool with full schema coverage, annotations, and an output schema, the description covers the main modes, ordering, status semantics, and cost, so an agent can call it confidently. The remaining gap is that multi-page retrieval and time-window (since/until) behavior are left entirely to the 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%, so the baseline is 3, but the description adds meaning not in the schema: deliveryId returns a single delivery including its payload, and skipped_backoff is a paused-webhook artifact rather than a send failure. Sampling of filters such as event/status/summary is left entirely to the schema.

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

Purpose4/5

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

The description identifies the resource precisely as a webhook's delivery log and enumerates the recorded fields (event, status, HTTP code, error, diagnosis), plus ordering ('newest first'), which clearly separates it from sibling tools like list_webhook_events or read_webhook_inbox. It never names those siblings explicitly, so differentiation is implied rather than stated.

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 states the two usage modes clearly: default listing versus 'Pass deliveryId for one delivery with its payload,' and it routes the paused-webhook case to catch_up_webhook. There is no explicit statement of when not to use it (e.g. versus list_webhook_events or clear_webhook_inbox), but the context is sufficient to choose correctly.

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

All Cito API tools Inspect

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

Need Help?