Compare two versions of a learned schema and get exactly which fields were added, removed or changed type, each flagged as breaking or not. This is the "why did my handler start failing" answer, produced without reading a single payload. from defaults to the version before to.
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | Target version number, or "current". | |
| from | No | Baseline version number (defaults to the one before "to"). | |
| schema_id | Yes | The schema id. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses a key behavioral trait—'produced without reading a single payload'—and explains the output includes breaking-change flags. This goes beyond the schema, though it omits details like error handling or permissions.
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?
The description is short, but the second sentence ends with a garbled fragment ('from defaults to the version before to.') that appears to be an incomplete thought. This structural issue makes it less polished and slightly confusing.
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 the tool has no output schema, the description does a good job of explaining the high-level return content (field-level changes with breaking flags). However, the confusing trailing fragment and lack of error/edge-case context prevent it from being fully complete.
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?
The schema descriptions cover 100% of parameters, so the baseline is 3. The description's only parameter-related addition ('from defaults to the version before to') is a confusing fragment that repeats the schema's default for 'from' without adding clarity.
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 the tool compares two schema versions and identifies added, removed, or type-changed fields with breaking-change flags. This specific verb+resource distinguishes it from siblings like get_schema or list_schemas.
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?
It provides clear context by framing the tool as the answer to 'why did my handler start failing', implying it should be used when investigating schema-related failures. However, it does not explicitly mention alternatives or when not to use it, so it falls short of full guidance.
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.
Each tool targets a distinct resource and action: buckets, events, schemas, deliveries, forwarding, verification, replay, and waiting. Even similar pairs like latest_event vs list_events are clearly differentiated by purpose, with no overlapping responsibilities.
Most tools follow a consistent verb_noun pattern with underscores, such as create_bucket, list_events, and delete_bucket. The only slight deviation is 'latest_event', which uses an adjective instead of a verb, but it remains intuitive and does not disrupt the overall predictability.
At 17 tools, the set is slightly above the typical well-scoped range of 3-15, but the domain covers buckets, events, schemas, deliveries, configuration, and more, so each tool serves a distinct and justified purpose. The count feels appropriate for the platform's breadth rather than excessive.
The set covers the primary lifecycle for buckets, events, and schemas, including create, read, list, and delete operations. However, there is no way to update or delete a forwarding rule after creation, and no explicit update operation for bucket metadata, leaving notable gaps in managing configurations.
