Inspect a CI build and receive its failed step and log cursor. Use read_build_logs next when status is failed.
| Name | Required | Description | Default |
|---|---|---|---|
| build_id | Yes | ||
| include_logs | No |
| Name | Required | Description | Default |
|---|---|---|---|
| status | Yes | ||
| build_id | Yes | ||
| started_at | No | ||
| finished_at | No | ||
| observed_at | Yes | ||
| repository_id | Yes | ||
| duration_seconds | No |
Changes observed during successful MCP inspections.
Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "build_id": {
+ "type": "string"
+ },
+ "duration_seconds": {
+ "type": [
+ "integer",
+ "null"
+ ]
+ },
+ "finished_at": {
+ "format": "date-time",
+ "type": "string"
+ },
+ "observed_at": {
+ "format": "date-time",
+ "type": "string"
+ },
+ "repository_id": {
+ "type": "string"
+ },
+ "started_at": {
+ "format": "date-time",
+ "type": "string"
+ },
+ "status": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "build_id",
+ "repository_id",
+ "status",
+ "observed_at"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses that it returns a log cursor, which is useful. However, it does not disclose whether the operation is read-only or if any side effects like marking the build as 'inspected' occur. It also doesn't mention authorization requirements. Given the lack of annotations, a 3 is appropriate; it adds some behavioral context but not exhaustive.
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 very concise, two sentences, with the most critical information (what it does and when to use) front-loaded. Every word is useful, no fluff. It is appropriately sized given the tool's complexity.
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 an output schema that likely describes the return structure, the description doesn't need to detail every field. However, there is a parameter (include_logs) that is not mentioned in the description, and the tool's purpose is not fully explored in relation to siblings. But since the output schema existston, a 3 is adequate; the description covers the essential but leaves some nuance for the output schema.
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 must compensate for both parameters. It mentions the 'log cursor' but not the include_logs parameter directly. The description implies that the tool returns a log cursor, which might relate to include_logs, but does not clarify how include_logs affects the output. It adds some meaning beyond the schema (the purpose of the build_id is implied) but not complete coverage.
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 verb 'Inspect', the resource 'a CI build', and the specific outcome: receiving the failed step and log cursor. It also hints at the return value (failed step and log cursor), which distinguishes it from generic inspection tools. It does not just restate the tool name.
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 explicitly tells the agent to use read_build_logs next when the status is failed, which is clear guidance on the follow-up action. It implies this tool is for initial inspection and directs to a sibling for logs. This is strong usage guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.