get_metrics

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

Without annotations, the description must carry behavioral disclosure on its own. It adds useful behavioral details like 'auto-detected if omitted' and default key sets, and 'Read' implies a non-mutating operation. However, it does not address error cases, availability of metrics, or any consequences of querying a run, so transparency is adequate but not rich.

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 front-loaded with a one-line summary followed by a compact Args block. Every sentence adds value and there is no filler or repetition, making it easy for an agent to scan and extract the essential information quickly.

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 description covers the tool's purpose and all four parameters with defaults and special cases, and an output schema exists so return-value details are not required. It is slightly incomplete in that it offers no guidance on prerequisites or comparison with related metric tools, but it is sufficient for correctly invoking 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?

Schema description coverage is 0%, so the description must fully compensate for missing parameter documentation. It does so: each parameter is explained with meaning, defaults, and special behavior (e.g., 'Use -1 for all' for last_n, 'auto-detected if omitted' for behavior_name). This is exactly the kind of semantic context the schema lacks.

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 begins with a strong verb and concrete resource: 'Read TensorBoard scalar metrics from a training run.' This clearly differentiates it from run-control and config tools, though it does not explicitly distinguish itself from similarly named siblings like get_training_logs, check_reward, or compare_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?

No guidance is provided about when to use this tool versus alternatives. The description does not mention situations where get_training_logs, check_reward, or compare_runs would be more appropriate, leaving the agent to infer usage from the tool name alone.

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