evaluate_cells

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

With no annotations, the description carries the full burden, and it delivers: persistent kernel state, state carrying between cells, document-order execution, summarization of large ranges, and forced full/summary output modes. This gives an agent a reliable mental model of side effects and performance behavior.

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?

Three sentences cover core mechanics, range syntax, interruption, and output modes without filler. Key behavioral facts are front-loaded, and every sentence earns its place.

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?

The description covers the most important behavioral and usage aspects, and an output schema exists so return-format details need not be repeated. Minor gaps remain for `timeout`, `stop_on_error`, and `notebook`, but defaults and names make these reasonably inferable.

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 clarifies `index` vs. `from_`+`to` and explains `detail` values well, but it leaves `timeout`, `stop_on_error`, and `notebook` semantics undocumented, forcing inference from names and defaults.

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 exactly what the tool does: evaluate notebook cells in document order in the persistent kernel, with state carrying between cells. It also differentiates itself from simpler siblings by explaining index vs. range evaluation, making the scope unmistakable.

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?

It gives explicit calling patterns: use either `index` or `from_`+`to` for a range, and use `detail='full'` or `'summary'` to control output verbosity. It also mentions `abort()` for interrupting long replays, but does not explicitly contrast with the `evaluate` or `batch` sibling tools.

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