replay_eventsAuthenticated tool for queueing replay by source, query, signature status, failed-delivery state, and time window.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | ||
| limit | No | ||
| sourceId | No | ||
| windowHours | No | ||
| signatureStatus | No | ||
| failedDeliveryOnly | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations (destructiveHint=false, readOnlyHint=false) indicate a write operation, and the description says 'queueing', but lacks details on side effects such as whether it creates a job, rate limits, or potential delays. The description adds minimal behavioral context beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single 15-word sentence is concise and front-loaded with the key action, but could be slightly more structured by listing filters in a clearer order or adding a second sentence for output description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 6 parameters, no output schema, and no parameter descriptions, the description is insufficient. It does not explain what the tool returns (e.g., confirmation, replay ID), error conditions, or success semantics, leaving the agent underinformed for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description must compensate, but only maps 5 of 6 parameters loosely ('source' for sourceId, 'query' for q, etc.) and omits 'limit'. It does not explain parameter interactions, allowed values, or constraints like the meaning of signatureStatus options.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'queueing replay' as the action, with specific filtering criteria (source, query, signature status, failed-delivery state, time window), distinguishing it from sibling tools like 'replay_event' and 'retry_failed_deliveries' which have narrower scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool requires authentication ('Authenticated tool') and is for queuing replays based on filters, but does not explicitly state when to use it over alternatives like 'replay_message' or 'retry_failed_deliveries', nor does it provide exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have distinct purposes, but there is some overlap between `list_messages`, `list_recent_events`, and `list_message_attempts`, and between `replay_event` and `replay_events`. However, the descriptions generally clarify differences.
The naming mostly follows a verb_noun pattern (create_, list_, get_, update_, delete_), with consistent snake_case. A few tools like `rotate_endpoint_secret` and `upsert_event_type` deviate but still use verb_noun structure.
With 52 tools, the set is extremely large and may overwhelm agents. While the domain is complex, this many tools reduce coherence and make selection more difficult.
The tool surface is very comprehensive, covering CRUD for most resources, replay, retries, anomaly management, and webhook setup. Minor gaps exist (no delete for destinations, no update for sources), but core workflows are well-supported.