get_metric_curve

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

No annotations are provided, so the description carries the burden; it does disclose that the curve is downsampled and that the last value is included, which is real behavioral context. It omits what happens for unknown metrics, the downsampling method, and any permission/limit behavior.

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?

A single front-loaded sentence with zero waste: verb, resource, qualifier ('downsampled'), examples, and the extra return element ('last value').

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 read-only curve lookup with no output schema and full parameter documentation, the description covers what is returned and the key qualifier (downsampling). Minor gap: no guidance on behavior for missing runs/metrics or on how many points to request.

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 100%, so baseline is 3, but the description adds meaningful examples of metric names (loss, train_psnr, num_gaussians) that the schema does not enumerate, helping the agent understand what 'metric' accepts.

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 and resource: 'Get a downsampled training curve of one logged metric plus its last value', with concrete metric examples. It distinguishes itself in spirit from get_final_metrics by emphasizing the curve and downsampling, but never names a sibling explicitly.

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 implies usage (fetch a time series for one metric) and the schema defaults ('loss', 10 points) hint at typical calls, but there is no explicit when-to-use guidance such as curve vs. get_final_metrics vs. compare_runs.

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