Get Experiment

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

With no annotations provided, the description carries the full burden, and it does disclose genuinely non-obvious semantics: aggregates are computed over completed runs only, std is population standard deviation, and a metric is None below 2 values. What it omits is the read-only/side-effect profile and any failure behavior when experiment_id does not exist.

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 that leads with the payload rather than preamble, and every clause conveys a distinct fact. The brace notation is dense but compact and readable for an agent parsing structure.

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 the description did not need to restate return values, yet it spends its entire length doing so. For a one-parameter read tool that is largely sufficient, but it leaves usage guidance and the read-only assurance unaddressed.

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 single parameter experiment_id is self-describing by name, so the low 0% schema description coverage is a small risk in practice. However, the description adds nothing about the parameter: no format, no statement of whether a name or ID is accepted, and no behavior on a missing or unknown ID.

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 the resource (an experiment) and specifies exactly what the snapshot contains: status, per-run rows, and aggregates. It is clear what the tool returns, but it never states the operation as a verb (e.g. 'retrieve') and does nothing to distinguish it from siblings like get_execution, get_results, or run_experiment.

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?

There is no guidance on when to call this versus the many adjacent tools (get_execution, get_results, run_experiment, list_executions). The only implied usage is 'once finished, aggregates are available', which hints at timing but not tool selection.

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