diagnose_ciClassifies failures in CI logs or JUnit XML reports—such as flaky tests, dependency conflicts, timeouts, compile errors, and assertions—and suggests a next step.
Classify the failures in a CI log or JUnit XML report (flaky test, dependency conflict, timeout, compile error, assertion, ...) and suggest a next step. Uses the ci-doctor CLI.
| Name | Required | Description | Default |
|---|---|---|---|
| log | Yes | Raw CI log text or JUnit XML | |
| input_format | No | auto |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint=true and openWorldHint=false, so safety and locality are covered structurally. The description adds one piece of genuine context - it is backed by the ci-doctor CLI - but says nothing about latency, log size limits, or the shape of the classification/suggestion it returns despite there being no output schema.
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?
Two tight sentences with the capability and its output front-loaded and the implementation detail (ci-doctor CLI) trailing. No filler or restatement of the tool name.
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-parameter read-only diagnostic with no output schema, the description covers what goes in and roughly what comes back (a classification plus a suggested next step). The main gap is the 'input_format' semantics and any handling limits for large logs.
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 50%: the required 'log' parameter is documented, but 'input_format' has only an enum and default with no explanation in either the schema or the description. The description's phrase 'CI log or JUnit XML' hints at the text vs junit distinction but never says when to override the 'auto' default, so the one undocumented parameter stays ambiguous.
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 names a specific verb (classify) and resource (failures in a CI log or JUnit XML report), enumerates concrete failure categories, and adds a second capability (suggest a next step). Nothing in the sibling set (list_tasks, get_task, start_session, run_in_sandbox, end_session) overlaps, so an agent can route to it unambiguously.
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?
Usage is only implied by the phrase 'a CI log or JUnit XML report' - there is no explicit statement of when to call this versus other tools, no prerequisites, and no exclusion such as when a log is too large or already parsed. Adequate but leaves the agent to infer the triggering condition.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.