study_start

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

With no annotations, the description carries the full burden. It discloses that the study is detached, bounded, serial single-stage, and that progress survives server exit, which is valuable operational context. It also notes preparation of isolated variants. It does not mention side effects on case files or resource cleanup, but the key behavioral traits are present.

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 dense but not wasteful; every clause contributes either purpose, syntax, or constraints. The specification and response examples are front-loaded after the one-sentence purpose. It could be slightly more readable, but it earns its length given the 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?

The description thoroughly documents the two required complex parameters but leaves the required `case_dir` entirely unexplained, and optional parameters such as `analysis_type`, `analysis_class`, `external_inputs`, `max_concurrency`, and `parameters_file` receive no guidance. Although an output schema exists, the input schema still has gaps that the description could fill, so completeness is adequate but not strong.

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. It provides detailed structure for the complex `specification` and `responses` parameters, including examples and allowed values like `combination:'product'|'zip'`, `component may be 'magnitude'`, and `reduction may be final/min/max`. It does not cover simpler parameters such as `case_dir`, `analysis_type`, or `max_concurrency`, but the most intricate and error-prone parameters are well explained.

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 explicitly states the action: 'Prepare all isolated variants, then start a detached bounded study.' This clearly distinguishes it from sibling tools like study_status, study_cancel, study_resume, and study_results, which operate on existing studies. The purpose is specific and actionable.

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 implies usage for parameter and mesh studies by detailing specification kinds, and it provides important constraints: 'Serial single-stage POSIX jobs only' and 'Progress survives server exit.' However, it does not explicitly call out sibling alternatives or state when not to use this tool, leaving the when-to-use vs. alternatives mostly implicit.

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