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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is carried. The description adds real context beyond that: it returns not just membership but the reason for failures, which tells the agent what to expect from the payload.

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 tight sentences with zero filler; the purpose leads and the disambiguation follows. Every clause carries information the agent needs.

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 six fully documented parameters and no output schema, the description covers purpose, input sourcing and sibling routing adequately. What it omits is the shape of the returned rows and pagination behavior, a minor gap given the complete schema.

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 100%, including the enum on status and the clarification that sequenceId is a step id, so the schema does the heavy lifting. The description reinforces the step-id semantics but adds no filter or pagination detail beyond the structured fields.

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+resource: which leads sit at a given step, plus failure reasons. The second sentence pins down its role as the drill-down behind the step counters, which cleanly separates it from sequence_step_stats.

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 explicit sourcing for the step id (`sequence_list` / `flow_get`) and names two alternatives with the conditions that select them: `lead_flow_state` for one lead's own position, `activity_skip` to unblock a stuck action. When-to-use and when-not are both covered.

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