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

Annotations already mark it read-only, idempotent, and non-destructive; the description reinforces that with 'without changing anything' and adds useful state-semantics context (undoable, undone, irreversible, unknown). This goes beyond simply restating the annotations, though it does not address auth or rate-limit 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?

Two tight sentences front-load the core behavior before the use case, and every phrase earns its place. The description is easy to scan and free of filler.

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?

For a single-parameter, read-only inspection tool with no output schema, the description covers the tool's purpose, output categories, and canonical use case. It leaves minor gaps around group_key semantics and error behavior, but nothing critical for deciding to call it.

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 schema provides only a string type and no description for group_key, and the description never names or explains the parameter. An agent must infer that group_key identifies the unit of work from the tool name; the description does not define its form, how to obtain it, or any constraints.

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 action and resource: it 'shows every step in a multi-step unit of work' and enumerates exactly which categories of step state are reported. This makes it easy to distinguish from sibling inspection tools like get_run or get_effect, which target different resources.

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 an explicit trigger context: use it to answer 'where did this workflow actually get to?' after a crash. It does not, however, contrast itself with sibling inspection tools or state when not to use it, so it stops short of full alternative routing.

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