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

With no annotations, the description carries the full burden and does substantial work: it discloses that a real voice agent is provisioned at the provider, that accept_incoming makes the number answer real calls, that the operation can take ~1 minute, and that setup is free while calls cost 25 credits/min. It omits update semantics (what an existing channel loses when re-run) and any permission/auth or failure/rollback behavior.

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 action and packed with signal; the parenthetical "(generated if omitted)" and the cost/latency sentences all earn their place. It reads as one long comma-spliced enumeration, which is dense but not padded.

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 an 18-param mutation tool with no annotations and no output schema, the description covers prerequisites, input sources, side effects, cost and duration. The main remaining gap is that with no output schema it never says what comes back (a connection/channel id?), which an agent would want before chaining calls.

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 33% with 18 parameters, so the description needs to compensate, and it largely does by naming the meaningful knobs in plain language (script "generated if omitted", inbound calls on/off, silence/reminder timings, pace, emotion, background sound). It adds real semantics for a few params but does not clarify the numeric ranges or the distinction between connection_id and phone_number_id.

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 pair and resource — "Create/update the agent's Voice Call channel" — and immediately enumerates the configuration surface (number, objective, script, voice, language, inbound, background sound, timings). This clearly separates it from preview_setup_phone_agent (the dry run) and from generic connection tools like create_agent_connection.

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 a hard prerequisite chain — "Only call after preview_setup_phone_agent and the user's approval" — and routes the agent to list_phone_numbers and list_retell_voices for inputs. It does not explicitly say when a different tool should be used instead (e.g. create_agent_connection or set_agent_contact_channels, which could also touch a PHONE_CALL channel), leaving one ambiguity among many siblings.

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