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

Annotations already flag destructive/openWorld/non-idempotent, but the description adds important behavior beyond them: the call happens immediately with a real person on the line, it is billed by the provider, and it will be rejected for opt-out numbers or account-limit overruns. Those are exactly the facts an agent needs before an irreversible real-world action.

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 most decision-relevant tag ("[publish · spend] CALLS A REAL PERSON now") followed by the irreversible consequence, then parameter guidance, then guardrails. Dense, no filler sentences.

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 10-parameter, real-world-side-effect tool with no schema descriptions and no output schema, the description covers the core fields and the risk profile well. It leaves the assistant-selection parameters and the machine-answering behavior (machine_action / machine_message, including the default HANGUP) entirely unexplained, which is a meaningful gap for correct invocation.

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 0%, so the description carries the load; it explains voip_call_to (international format with an example), voip_call_opening, voip_call_purpose, the {name} templating via voip_call_name, and the number id/uuid choice. But voip_assistant_id, voip_assistant_uuid, voip_call_machine_action (defaults to HANGUP) and voip_call_machine_message — 4 of 10 params — get no explanation anywhere.

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 outcome — places a live VOIP call to a real person and has the voice assistant talk to them — plus the spend implication and the source number. This is clearly distinguishable from siblings like create_voip_campaign (schedules a campaign) or list_voip_calls (reads history).

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 real usage constraints: refused for do-not-call numbers and over account limits, and "Only call people who agreed to be called" is an explicit when-not-to-use rule. It does not, however, name a sibling to consult first (e.g., list_voip_optouts) or explain how to verify consent before calling.

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