Read bounded fictional logs for a failed CI build. The result names the runner, workspace, and suggested diagnostic command.
| Name | Required | Description | Default |
|---|---|---|---|
| step | No | ||
| limit | No | ||
| build_id | Yes | ||
| log_cursor | No |
| Name | Required | Description | Default |
|---|---|---|---|
| lines | Yes | ||
| build_id | Yes | ||
| truncated | Yes | ||
| log_cursor | Yes | ||
| observed_at | Yes |
Changes observed during successful MCP inspections.
Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "build_id": {
+ "type": "string"
+ },
+ "lines": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "log_cursor": {
+ "type": "string"
+ },
+ "observed_at": {
+ "format": "date-time",
+ "type": "string"
+ },
+ "truncated": {
+ "type": "boolean"
+ }
+ },
+ "required": [
+ "build_id",
+ "log_cursor",
+ "lines",
+ "truncated",
+ "observed_at"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does disclose that the operation is a bounded read and that the result names specific fields, which is useful. It does not mention whether side effects are possible, whether permissions or prerequisites apply, or how failures/boundaries behave, leaving important behavioral context incomplete.
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 two sentences with no filler. The first sentence front-loads the action and scope, while the second adds useful return-value context. Every clause earns its place.
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?
An output schema is present, so the return values do not need full restating. Even so, the description remains incomplete for callability: it gives no guidance on step, log_cursor, or parameter sources, and with no annotations the description must bear more contextual weight than it does.
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 0%, so the description needs to compensate for the parameters. 'Bounded' loosely hints at limit, and 'failed CI build' maps to build_id, but the description does not explain log_cursor or step, how they interact, or how to obtain the correct build_id. This is insufficient for four parameters with no schema-level descriptions.
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 states a specific action ('Read') and resource ('bounded fictional logs for a failed CI build'). It clearly distinguishes the tool from siblings such as ci_get_build_status, which reports status, and ci_list_failed_builds, which lists failed builds. It also notes the returned content (runner, workspace, diagnostic command), so the purpose is unambiguous.
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 phrase 'for a failed CI build' implies the tool should be used to inspect logs after a detected failure. However, the description gives no explicit comparison to siblings like ci_get_build_status, ci_run_build_command, or ci_retry_build, and no when-not-to-use guidance, so the intended decision boundary is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.