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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower, and the description adds genuine context: the AI summary is conditional ('if enabled') and outputs can be suppressed to shrink the payload. It does not mention cost, size, or pagination characteristics of large result sets.

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?

Front-loaded with the payload contents, then the toggle guidance, then a compact example. Efficient, though the example call partially duplicates the schema's examples array and the comma-separated return list is 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?

With no output schema, the description correctly carries the return-value burden and does so by listing aggregates, cells, and the optional summary. Minor gaps remain: it does not say how the summary is enabled or what the result looks like for a still-running experiment.

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 coverage is 100%, so the baseline is 3, but the description goes beyond the schema's terse 'include full model outputs per cell' by stating the concrete benefit of false (aggregates only), making the tradeoff actionable. experiment_id's provenance ('From experiment_create') is already in the 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?

The description names a specific resource and enumerates its contents (per-model aggregates, per-cell outputs, AI summary), which lets an agent distinguish it from experiment_status and experiment_list without opening the schema. It is a clear retrieval verb with a well-scoped payload.

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 real guidance on the include_outputs:false switch ('aggregates only'), which is useful steering. However, there is no when-to-use framing relative to siblings such as experiment_status (progress) or experiment_list (discovery) — usage context is implied rather than stated.

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