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

Annotations already cover safety (readOnly, idempotent, non-destructive), so the bar is lower; the description adds real behavioral detail beyond them: aggregates are computed over completed runs only, std is population standard deviation, and the value is None below 2 samples. These semantics are not derivable from the annotations or schema.

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?

Compact and front-loaded with the returned content; the parenthetical field lists and formula caveats are dense but each clause carries information. It is telegraphic rather than wasteful, though the nesting of braces makes it slightly harder to scan.

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 explaining return values is not strictly required, yet the description does so coherently and covers the finished-vs-running distinction. Combined with full schema coverage and annotations, an agent has enough to call it correctly; only the absence of usage routing is a gap.

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?

Only one parameter exists and schema description coverage is 100%, with the schema already noting it comes from experiment.run. The description adds nothing about the experiment_id beyond what the schema states, so the baseline 3 applies.

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 states the specific resource (an experiment snapshot) and enumerates what it contains: status, per-run rows, and aggregates. It is clearly a read/inspect tool, distinguishable from experiment.run and execution.get, though it never uses an explicit verb like 'retrieve' or 'inspect' and reads more like a return-shape spec.

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 explicit when-to-use guidance and no mention of alternatives such as execution.get or execution.results. The only implicit cue is 'once finished', hinting at polling, but the agent is left to infer the calling context entirely.

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