update_agent

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

With no annotations provided, the description carries the full behavioral burden. It discloses the key trait — PATCH-like partial update ('Only provide fields you want to change') — which prevents an agent from clobbering unspecified fields. However, it does not disclose error behavior, the effect of toggling isActive, permissions, or reversibility, leaving a thin profile for a write operation.

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 short sentences with zero waste. The first establishes verb and resource; the second delivers the crucial partial-update semantics. Nothing repeats schema content or adds filler.

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 12-parameter mutation tool with no annotations and no output schema, the description omits what the call returns on success and how failures surface. It does cover the two essentials for a correct call — target identity via required id and partial-update semantics — and the schema carries enum and required constraints, so the main gaps are around response shape and consequences.

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 only 42%, leaving language, llmModel, ttsVoice, webhookUrl, asrProvider, llmProvider, and ttsProvider undocumented in the schema. The description must compensate but mentions no parameter specifics, formats, constraints, or enum guidance — the only parameter-level contribution is the general 'only provide fields you want to change' rule already implied by 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 ('Update') plus a specific resource ('existing voice AI agent'). The verb alone cleanly distinguishes it from siblings list_agents, get_agent, create_agent, and delete_agent, so an agent can select it without opening the 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?

'Only provide fields you want to change' gives clear in-tool usage guidance and signals partial-update semantics, while 'existing' implies the target must already exist, naturally pairing with create_agent for new agents. It never explicitly names alternatives or states when not to use it, so exclusions rely on inference from sibling names.

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