exp_generate_reports

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

With no annotations provided, the description carries the full burden of behavioral disclosure, but it says nothing beyond the action itself. It does not state whether reports are written to the given directory, whether api_key triggers a paid/billable service call, whether the operation is read-only or creates files, or what side effects the agent should expect.

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 a single tightly worded sentence with no wasted text, and the action is front-loaded. However, the brevity is more a result of omission than distillation — compared to the very sparse 'Process' floor, there is enough substance here to warrant a midpoint score, but it does not demonstrate the efficient completeness of a genuinely polished definition.

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 tool with no annotations and no output schema, the description should at minimum hint at output format/location and prerequisite data, but it does neither. The schema is simple (two flat string params), so the ceiling is modest, but an agent is left guessing whether it needs an api_key, what the report looks like, and whether it modifies the project directory.

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 50%: the directory parameter has a one-line schema description while api_key is completely undocumented. The tool description adds nothing about either parameter, leaving api_key's purpose, format, and optionality entirely opaque. The description fails to compensate for the schema's coverage gap.

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 verb ('Generate') and resource ('experiment comparison reports'), and the 'experiment' prefix separates it from the many other report generators in the sibling list (llmeval_generate_reports, dq_generate_reports, cost_generate_report). However, it does not explicitly differentiate from the closely related exp_setup_tracking and exp_add_metrics siblings, and 'comparison' is left slightly vague (comparing what against what).

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?

No when-to-use guidance is provided. The description does not say whether this tool should be run after exp_setup_tracking or exp_add_metrics, what prerequisites must exist (e.g., experiment data already collected), or when a sibling like exp_add_metrics would be the better choice. The 'Pro feature' note is a constraint, not usage guidance.

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