Training and evaluation datasets curated from an agent's completed runs. Each row carries the source agent, how many runs it was cut from, the target verifier and the fixture manifest it is bound to. Answers: 'what datasets do we have?', 'is there a dataset for this agent?'.
| Name | Required | Description | Default |
|---|---|---|---|
| agentId | No | Filter to one agent (optional — all datasets if omitted) | |
| customerId | No | (Converra superadmin only) Target customer ID |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds real behavioral value beyond that by spelling out the shape of each returned row (source agent, run count, target verifier, fixture manifest) in the absence of an output schema. It stops short of pagination or ordering behavior, keeping it from 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three tight sentences, front-loaded with the resource definition before the question framing. Every sentence carries content, though the row-content sentence could be seen as slightly more than strictly needed for a listing tool.
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?
For a two-optional-param read-only list with no output schema, the description supplies the return shape and usage context an agent needs. It is largely complete; only sibling routing and pagination behavior are missing.
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?
Schema description coverage is 100%, so agentId and customerId are already fully documented (including the superadmin-only caveat). The description adds no filter semantics beyond the schema, so the baseline 3 applies.
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?
States a clear resource (training/evaluation datasets curated from completed runs) and implies the list verb, and clarifies the unit of return ('each row carries the source agent...'). However, it never distinguishes itself from near-name siblings like list_dataset_versions, list_dataset_examples, or get_dataset, so an agent must still infer the boundary.
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 'Answers: ...' framing implies when to reach for it (inventory questions, checking for an agent's dataset), which is useful implied usage. But it names no alternatives and no exclusions — nothing tells the agent to use list_dataset_versions for version history or get_dataset for one dataset.
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.