list_metric_groups

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

With no annotations, the description carries the full burden and does a fair job: it discloses newest-first ordering, the null-vs-populated semantics of each entry's ``last_run``, that an error message may be returned instead of data, and the object-store side effect with ``@obj_...`` IDs. It stops short of permissions or rate-limit behavior, but the disclosed traits are concrete and non-obvious.

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 tool-specific content is front-loaded and dense with signal, but the closing four sentences of object-store boilerplate repeat each other ('can be referenced in other functions' vs 'pass this result to other functions'). That template padding dilutes an otherwise tight 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?

No output schema and no annotations exist, so the description must cover behavior and returns itself, and it largely does: entity definition, ordering, the ``pipeline_name`` effect on ``last_run``, error returns, and the object-store handoff are all present. The main gap is that a single-param tool is simple enough that this is close to sufficient without being exhaustive.

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 for the lone ``pipeline_name`` parameter, and it does: it explains that the parameter attaches each group's most recent scoring run on that pipeline, described without the grid (status, ``selection``, timing), and yields null when the group never ran there. That is meaning well beyond the bare ``anyOf[string, null]`` schema.

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 ('Lists the workspace's Metric Groups') plus an ordering ('newest first'), and then defines what a Metric Group is, which is what separates it from entities like evaluators or experiments in the sibling set. It never explicitly names a sibling to route away from, but the entity definition does the disambiguating work.

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 explains the effect of ``pipeline_name`` and routes the agent to ``get_experiment_run`` for reading a run's results, which is useful contextual guidance. It does not state when to prefer this tool over the other list_* siblings or any preconditions/exclusions, so usage remains implied rather than explicit.

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