get_batch_errorsList a batch's items that did not succeed (status failed, blocked, cancelled or budget_exceeded), each as get_batch_items lists it: { items, nextCursor, hasMore }, in pages of up to 100 (cursor, limit). A URL robots.txt refused is among them, blocked with its blockReason.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| debug | No | Keep each item's usage and trace. Default false. | |
| limit | No | ||
| cursor | No |
Changes observed during successful MCP inspections.
Input schema / properties / debugAdded value: +{
+ "description": "Keep each item's usage and trace. Default false.",
+ "type": "boolean"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description goes further by disclosing the return shape ({ items, nextCursor, hasMore }), the page size limit of 100, and the blockReason semantics for robots.txt-refused URLs, adding genuine behavioral context.
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 dense sentence, front-loaded with purpose before qualifications. Efficiently packs statuses, return shape, pagination, and edge-case behavior, though the run-on structure slightly reduces readability.
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?
With no output schema, the description correctly supplies the return shape and pagination envelope, plus the non-obvious status enumeration that defines what an 'error' is. Minor residual gaps remain around the id parameter and debug semantics.
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 coverage is only 25% (only 'debug' is documented in the schema), so the description must compensate. It clarifies cursor and limit semantics ('in pages of up to 100 (cursor, limit)'), but leaves 'id' and the debug flag unexplained, so compensation is partial.
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 specific verb and resource ('List a batch's items') and explicitly scopes it to non-success statuses (failed, blocked, cancelled, budget_exceeded). It also names the sibling it mirrors with identical output shape ('as get_batch_items lists it'), letting an agent distinguish it from get_batch_items and get_batch without opening a schema.
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 status filter clearly implies when this tool is appropriate versus get_batch_items (all items), giving strong context for selection. However, it never explicitly says 'use this instead of get_batch_items when...' nor names an exclusion condition, so it falls short of fully explicit routing.
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.