train_metrics

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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses the dual-mode behavior and that the returned series is downsampled, which is real behavioral information. It omits any note on auth/permissions, error behavior, or the effect of max_points on downsampling, leaving notable gaps for an annotation-free tool.

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 no filler; the resource is stated first and the mode logic follows. Efficient and readable, though the colon-separated clauses are slightly dense.

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?

An output schema exists, so return values need not be described, and the key tag-mode behavior is covered. run_name is self-evident and max_points has a schema default. The description is nearly complete, missing only explicit max_points semantics.

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 compensate. It explains the tag parameter's two modes well (null lists names, a value returns the series), but says nothing explicit about run_name or max_points beyond the passing hint 'downsampled'. Partial compensation, not full.

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 resource and scope: 'TensorBoard scalars for a run', with a clear verb-implied retrieval action. It is not a tautology and the two operating modes (tag absent vs present) are stated. It does not, however, explicitly differentiate itself from siblings like train_logs, so it falls short of a 5.

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 tag lists tag names; a tag returns its series' tells the agent how to switch between the two modes, which is genuinely useful selection guidance within the tool. But there is no explicit when-to-use guidance versus alternatives such as train_logs or train_checkpoints, leaving sibling routing to inference.

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