update_agent

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

Annotations only declare idempotentHint, so the description carries the remaining burden. The partial-update disclosure is genuinely useful behavior beyond the annotation. However, the voice_mode/system_prompt dependency largely restates the schema's own 'Required when voice_mode is hosted' note, and nothing is said about permissions or side effects.

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?

Two sentences, front-loaded with the verb+resource, and the second sentence carries the highest-value constraint. Nothing is padded or repeated.

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 and a rich 19-parameter input schema, the description supplies the two things the schema can't: patch semantics and a cross-field precondition. Complete enough for correct invocation, though it omits any note on what the response returns after an update.

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% and the schema already documents ranges, enums, defaults, and formats for all 19 fields. The description names field groups but adds no syntax or format detail beyond the schema, so it sits at the baseline 3.

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 (update) and resource (agent configuration), then enumerates the configurable surface: name, description, voice, instructions, greeting, transfer, voicemail. An agent can immediately tell this is the mutation counterpart to create_agent/get_agent. It stops short of explicitly naming a sibling, so it lands at 4 rather than 5.

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?

'Only provided fields are updated' gives the caller clear patch-semantics guidance and the co-requirement for hosted mode is a concrete precondition. There is no explicit when-to-use-this-vs-sibling routing (e.g., when to prefer update_agent over create_agent), which keeps it out of the 5 band.

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