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

Annotations declare only destructiveHint=false, leaving the read/write boundary to the description, and the verbs make the mutation nature clear. The description adds a little context about what set_primary means (the account's fallback agent), but says nothing about permissions, reversibility, or side effects on existing agents, so it does not go much beyond the schema's own action descriptions.

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 with no waste: the first front-loads the full action set, the second handles routing to the correct sibling tools. Every clause earns its place.

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 but full parameter coverage in the schema and a non-destructive annotation, the description covers the action scope and sibling routing well. It omits prerequisite/permission context and what happens to existing agents on create/set_primary, but is largely sufficient 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 description coverage is 100%, so all four parameters are already documented in the schema, and the baseline is 3. The description adds only a cross-reference that voice_id values come from list_voices, which is marginal value beyond the structured fields.

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?

The description states specific verbs (create, duplicate, rename, set voice, set primary) against a specific resource (an AI agent), and routes the agent away from siblings by naming update_settings for wording/knowledge and list_voices for voice selection. An agent can distinguish this tool from update_settings and list_voices without opening either 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?

It explicitly names the alternative for adjacent tasks ('Edit an agent's wording and knowledge with update_settings (entity ai_agent)') and where voices come from ('pick voices from list_voices'), which is clear routing guidance. It stops short of stating prerequisites, permissions, or when NOT to use the manage actions themselves, so it is strong but not complete.

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