Launch Study Run

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

The description richly supplements the annotations by explaining retry behavior with submission_key reuse, warning against inventing new keys, and noting that budget conflicts require inspection rather than a new attempt. It also clarifies that the tool never opens existing results, which is useful beyond readOnlyHint/idempotentHint.

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 every sentence carries operational value. It front-loads the core purpose, then adds prerequisites, retry protocol, conflict handling, and engine-change remediation in a logical order without unnecessary filler.

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 output schema exists and annotations cover safety/mutation semantics, the description completes the picture: prerequisites, budget behavior, retry key discipline, and engine-change re-freeze workflow. An agent has enough information to invoke this tool correctly and to know when to route to sibling tools.

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?

With only 25% schema description coverage, the description compensates by contextualizing all four required parameters: study_id must be active, revision_id must be frozen and executable, policy_id must be an active same-study policy, and submission_key is the caller-generated retry identity. This is meaningful semantic guidance beyond the bare 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 names a specific action and resource: 'Launch a NEW fit of a frozen revision within study attempt/concurrency budgets; it never opens existing results.' This clearly distinguishes the tool from sibling read-only tools like get_study_run or list_study_runs by emphasizing new launches rather than result inspection.

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?

It gives explicit when-to-use guidance: call get_launch_eligibility first, ensure an active study, a frozen revision on the current engine, and an active same-study policy. It also gives when-not-to-use guidance for budget/state conflicts and points to refreeze_recipe_revision when engine_changed occurs.

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