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

Annotations already establish non-read-only, non-destructive, closed-world behavior. The description adds meaningful behavior beyond that: fresh turn_id per step, idempotent replay returning the stored step, and the instruction to surface wall.for_human when present. It could say more about what state is mutated, but the idempotency and wall handling are substantive.

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?

It is compact, front-loaded with the primary usage rule, and every sentence contributes: usage, return shape, action selection, idempotency, and wall handling. No filler or repetition.

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 complex multi-action tool with no output schema, the description covers the main flow, return fields, idempotency, and special wall handling. The only notable omission is explaining when or why to use the resume action, which leaves that branch incomplete.

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 67%, and the description meaningfully clarifies action semantics beyond the schema: pick versus say conditions, go targeting a contract stop, and drill/simulate/exit contexts. It still omits the resume action entirely, so one action variant is left for the schema alone to define.

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?

States a specific verb and resource (take_journey_step) and immediately scopes it to 'every step after open_journey', distinguishing it from the sibling open_journey tool. It also says what the tool returns: the next step with answer/statement/options/media/progress/limits.

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?

Gives clear selection rules: use after open_journey; send pick when the user chose an option or number, otherwise send say. It also explains go, drill, simulate, and exit action contexts, though it never mentions the resume action, leaving that branch undocumented.

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