exp_add_metrics

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

With no annotations, the description carries the full behavioral burden. It only conveys that the operation is an 'add' (a mutation), but it does not disclose whether files are written, an API is called, authentication is needed, or what side effects or return values can be expected.

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 text is short and free of filler, with the main action front-loaded. However, the terseness crosses into under-specification: there is no contextual framing, so brevity is achieved at the expense of a self-contained description.

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 tool has no annotations and no output schema, so the description needed to clarify what 'custom metric tracking' means, where the metrics are registered, and whether an existing experiment tracking setup is required. None of this is present, leaving an agent without enough context to confidently invoke the tool.

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 description adds no meaning to the parameters. The schema documents 'directory' with 'Project directory,' but 'api_key' has no description, giving only 50% schema coverage. The description does not compensate by explaining how the api_key or directory are used or how to specify the custom metric.

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 states a recognizable verb-plus-resource: 'Add custom metric tracking.' This is clear at a surface level and is not a tautology, but it does not differentiate the tool from siblings like exp_setup_tracking or jobdash_add_metrics, and it leaves the experiment/domain scope implicit.

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 guidance is given about when to use this tool rather than an alternative. There is no mention of prerequisites such as exp_setup_tracking, no exclusions, and no indication of whether this should be called before or after other experiment-related tools.

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