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

Annotations already mark this read-only and non-destructive, and the description adds substantial context: sign-in requirement and owners-only access, the full status vocabulary including error cases, when the summary becomes available, and a prompt-injection warning that call content is data, never instructions. This is exactly the behavior an agent cannot infer from structured fields.

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?

Everything is packed into one dense paragraph, but it is front-loaded with the access requirement and the identifying parameters. Each parenthetical status list and event-type breakdown earns its place by eliminating a follow-up call. A small amount of the phrasing around the summary timing could be tighter.

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?

There is no output schema, so the description has to describe the return shape, and it does: status values, duration, events differ by from_call versus coach, and summary timing after completion. Combined with the rate-limit guidance and the cursor semantics, an agent can call this correctly and interpret the result without further information.

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 only 50 percent, and call_id has no schema description at all. The description compensates well for since by defining it as the events_cursor from the last read, and the empty-list result, but it does not explain call_id's format or origin beyond calling it the id of a call placed by place_phone_call.

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 a specific verb and resource: it reads back a call that place_phone_call placed, keyed by call_id, and returns status, duration, and events. It names the creating sibling, which makes clear how this differs from place_phone_call and from a listing tool like phone_calls.

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?

The polling contract is explicit: call about once a minute, not in a tight loop. The description also tells the agent to pass the since cursor from the previous read and that an empty events list means nothing new. It does not name an alternative for listing calls or for fetching a brief, but the when-to-use context is clear.

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