Inspect local CI workflow configuration without accessing credentials or remote status.
Inspect local CI workflow configuration without accessing credentials or remote status.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| raw | No | ||
| tool | No | ||
| engine | No | ||
| status | No | ||
| metrics | No | ||
| summary | No | ||
| findings | No | ||
| metadata | No | ||
| artifacts | No | ||
| duration_ms | No | ||
| review_kind | No | ||
| engine_version | No | ||
| review_provider | No |
Changes observed during successful MCP inspections.
v0.2.2Output schema / properties / metrics / anyOfPrevious value: -[
- {
- "additionalProperties": {
- "anyOf": [
- {
- "type": "integer"
- },
- {
- "type": "number"
- },
- {
- "type": "string"
- }
- ]
- },
- "type": "object"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "additionalProperties": {
+ "anyOf": [
+ {
+ "type": "integer"
+ },
+ {
+ "type": "number"
+ },
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "type": "object"
+ },
+ {
+ "type": "null"
+ }
+]v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full behavioral burden, and it delivers on the key safety trait: it states the tool is inspect-only and explicitly does not access credentials or remote status. This is genuinely valuable pre-invocation knowledge an agent cannot get elsewhere. It stops short of describing output shape or error/edge behavior, but an output schema exists to cover returns.
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 sentence that front-loads the verb and resource and appends the behavioral constraint. There is zero filler, and the length is appropriate for a one-parameter inspection 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?
The tool has a small surface area (one required param, output schema present), and the description covers purpose, scope, and a key behavioral boundary. Gaps remain: 'path' semantics are undocumented, and no sibling is named for remote-status or credential-requiring cases, but the information needed to invoke the tool is largely present.
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% and the description never mentions the single 'path' parameter directly. The agent can only infer from the tool purpose that 'path' likely points to the CI workflow configuration, with no clarification of file vs directory, relative vs absolute, or accepted formats. The description does not compensate for the schema's complete lack of documentation.
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 opens with a specific verb and resource ('Inspect local CI workflow configuration') and adds meaningful scope constraints ('without accessing credentials or remote status'). This helps distinguish the tool from remote-status CI tools and credential-touching operations among the large sibling list, though it never names an alternative sibling explicitly.
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 constraint 'without accessing credentials or remote status' implies the tool is for local, offline inspection, which gives the agent a sense of when it applies. However, no alternative tool is named and no explicit when-to-use/when-not-to-use conditions are given; the agent must infer applicability from the negative scope rather than being told.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.