compare_runs

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

No annotations are provided, so the description carries the behavioral disclosure burden. It explains the 'trend' and 'last_n' behavior, but does not explicitly state that the tool is read-only, what happens if a run lacks the metric key, or whether runs must be in a specific state.

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 purpose is front-loaded in one clear sentence, followed by a compact Args section with no filler. Every line adds useful information for calling the tool correctly.

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 simple 3-parameter comparison tool, the description covers all parameters, required and optional, with practical examples and edge-case handling. The presence of an output schema means return-value documentation is not required, and the description is sufficiently complete for an agent to invoke the tool correctly.

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 schema provides only names, types, and defaults, while the description adds real semantics: run_ids are explicitly a list, metric_key gets a concrete TensorBoard example, and last_n explains 'trend' inclusion plus the special -1 behavior for all points. This fully compensates for the 0% schema description coverage.

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 uses a specific verb and resource: 'Compare a specific metric across multiple training runs'. It clearly distinguishes this from sibling tools like get_metrics or list_runs by emphasizing multi-run comparison and hyperparameter tuning.

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 provides clear usage context with 'useful for hyperparameter tuning' and implies the appropriate scenario: comparing the same metric across multiple runs. It does not explicitly name alternatives or exclusion conditions, so it falls short of a 5.

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