Create a test plan before writing test code. Define the change, risk level, and existing tests to generate a structured testing strategy.
Create a test plan before generating test code
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | Model | |
| change | Yes | Change | |
| provider | No | Provider | auto |
| risk_level | No | Risk level | medium |
| preview_only | No | Preview only | |
| existing_tests | No | Existing tests |
Changes observed during successful MCP inspections.
v1.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must fully disclose behavior, but it only states the action ('create a test plan') without explaining side effects, required inputs, or output format. This is a significant gap for a tool that likely involves planning and may interact with external systems; the description provides minimal behavioral insight.
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 a single, concise sentence with no superfluous words. It is efficiently structured and front-loads the main action, making it easy to parse. This is good conciseness, though it could have included more detail without being verbose.
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 complexity of 6 parameters and no output schema, the description should provide more context about how run parameters like risk_level, model, and provider affect the test plan. It does not specify what the tool does with existing_tests or preview_only, leaving the agent with incomplete information to call it correctly. The output schema is absent, so the description should clarify return value expectations to avoid ambiguity.
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?
The input schema has 100% coverage, meaning every parameter has a description, but these descriptions are minimal (e.g., 'Model', 'Change'). The description itself does not add any context about the parameters. Since schema coverage is high, the baseline is 3, but the description does not go beyond the schema to clarify parameter semantics or relationship to the test plan.
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 'Create a test plan before generating test code' clearly states a verb ('Create') and a resource ('test plan'), and implies a purpose related to testing, which helps differentiate it from tools like coeus_generate_tests that generate code directly. However, it lacks explicit detail on what the test plan contains or how it is used, making it somewhat vague about the specific output.
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 suggests a sequential step ('before generating test code') but does not explicitly state when to use this tool versus alternatives like coeus_generate_tests or coeus_eval_plan. It mentions a relationship to generating test code, but does not provide clear exclusions or alternatives, leaving the agent to infer usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.