create_test_plan

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It discloses the approval workflow and plan contents but does not mention side effects, auth requirements, or whether the plan is stored. Lacks details on mutation or persistence.

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?

Front-loaded with main purpose, uses bullet points for plan contents, and clear flow instructions. No wasted sentences, well-structured for quick comprehension.

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?

No output schema, so description should explain return format. It describes the plan's contents but not how the output is structured (e.g., object fields). Agent needs to know what to present to user. Also lacks runtime details or error conditions.

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 100% with param descriptions. The description adds context: analysis is from analyze_for_testing, and priority enum is explained with 'all=full suite | critical=CRITICAL only | smoke=first 3 tests', which goes beyond schema.

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 it generates a detailed expert test plan from an analysis result, specifying the resource and verb. It lists plan contents (CRITICAL, MAJOR, MINOR tests, scripts, runtime) and distinguishes the tool from siblings like generate_atf_tests.

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?

Explicitly marks this as the approval step, instructs to present the plan and ask for user approval before calling run_approved_tests. Provides clear context for when to use, though no explicit when-not or alternative tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.