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

Annotations already mark it read-only, idempotent, non-destructive, so the safety profile is covered. The description adds meaningful behavior beyond that: it is a long-poll that blocks up to 50 seconds until state changes, and it surfaces questions that require a follow-up call. It does not mention rate limits or cost of repeated polling, a minor gap.

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?

Densely packed but front-loaded: purpose first, then payload contents, then the follow-up action, then polling and the default. It is a single sprawling sentence, but nearly every clause 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?

With no output schema, the description carries the return-value burden and does so: it enumerates the results table columns, the pending-questions section, totals, and spend. Combined with the polling and default behavior, an agent has everything needed to call and interpret 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?

Schema coverage is 100%, so baseline is 3, but the description adds real meaning: wait_seconds makes the call block until something changes (not just a timeout), and omitting batch_id explicitly falls back to the most recent batch. That clarifies intent beyond the terse schema strings.

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 exactly what is returned (batch progress: totals, results table, pending questions, spend) and scopes it to a call_around batch, which cleanly separates it from get_call, list_calls, and stop_batch. An agent can identify the tool and its payload without opening the schema.

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 actionable routing: answer pending questions with answer_question right away, and use wait_seconds (up to 50, 45 while running) to poll. It also explains the default when batch_id is omitted. It stops short of explicit when-not-to-use guidance versus siblings like get_call.

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