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

Annotations declare this is a mutating, non-idempotent, open-world, destructive operation, and the description adds the genuinely important behavioral fact beyond them: the call blocks the agent's turn until completion, and per-call overrides of system_prompt/greeting do not persist. It does not restate the annotation semantics, which is correct, but it also does not mention failure modes (unanswered calls, dial errors) or that a real phone call incurs cost.

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?

Front-loaded with the two highest-value facts (blocking behavior, return payload), then constraints, then defaults — a sensible order with no filler. The closing sentence about the optional agent and per-call overrides largely duplicates what already appears in the schema descriptions of agent_id, system_prompt, and greeting, so it is slightly redundant.

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 10-parameter blocking side-effecting tool with no output schema, the description covers the essentials: that it blocks, what it returns, how the target is specified, and how defaults resolve. Timeout semantics are handled in the schema rather than here, but error/abort behavior and the absence of any output schema mean the agent still cannot fully predict what a failed or partially completed call returns.

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%, so every parameter is already documented in the schema, making 3 the baseline. The description does add one thing the schema cannot express — the mutual exclusivity of contact_name/contact_id/to_phone — plus the agent default resolution and the fact that system_prompt/greeting overrides are scoped to this call only; the remaining fields (speed, from_phone, voicemail_behavior, max_wait_seconds) are left entirely to the schema.

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 ('Place an outbound call through Phone Bud') plus the effect an agent most needs to know: it BLOCKS until the call ends. It also enumerates what comes back (full transcript plus summary/action-items), so the tool is distinguishable from sibling get_call/start_campaign without opening any 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 concrete selection rules for the target parameter ('exactly one of contact_name, contact_id, or to_phone') and explains the agent fallback chain (favorite agent, else first available). It stops short of naming when to prefer an alternative path — e.g. that get_call exists for non-blocking follow-up, which only appears buried in the max_wait_seconds schema description.

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