tune

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

With no annotations, the description carries the full burden and does well: it discloses that each trial is a run, that the call blocks until budget is spent, and that budget is capped at 40. It omits whether the run persists artifacts or requires specific auth, but the expensive/blocking nature is clearly surfaced.

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?

Three dense sentences, front-loaded with the core action, then strategy options, then blocking/budget warning. Efficient with little waste, though the parenthetical GP detail is optional.

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 7-param, nested-object tool with no annotations and no output schema, the description covers behavior and key params but never states what the call returns (e.g., best params/metric) or how to inspect resulting trials via list_runs/get_run. Adequate but with a clear gap on return semantics.

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 only 43%, so the description must compensate, and it does for the key params: strategy values (grid | random | bayes with GP+EI), budget (max 40), objective (headline metric), and minimize (overrides catalogue direction). Space and params are left to the schema; name is unexplained.

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?

States a specific verb+resource: 'Search a parameter space for the best headline metric.' The tool's distinct behavior (tuning/optimization) is clear, though it does not explicitly contrast itself with siblings like run_campaign or run_experiment that also consume runs.

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?

Gives useful context ('keep budget small (max 40)') and notes direction comes from the catalogue unless minimize is given, but offers no explicit when-to-use-this-vs-alternatives guidance relative to run_campaign/run_experiment. Usage is implied rather than stated.

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