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

Annotations (readOnlyHint=false, openWorldHint=true) already indicate a mutating, open-world operation. The description adds valuable behavioral context: every mutation is versioned and reversible via rollback_config, and it discloses that compliance features (AI-disclosure, consent handling) are automatically applied. It does not contradict annotations and enriches the safety profile beyond what annotations convey.

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?

The description is structured and efficient: it front-loads the core purpose in the first sentence, then adds versioning and compliance details in subsequent sentences. It avoids redundant phrasing and each sentence carries distinct information. It is slightly longer than strictly necessary but remains clear and well-organized.

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 an output schema present and annotations covering the basic safety profile, the description covers the essential context: it defines the agent concept, notes the versioning/reversibility mechanism, and highlights compliance behavior. It does not detail error handling or return values, but these are either covered by the output schema or less critical for an initial creation call.

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 100%, so the schema fully documents all 8 parameters. The description adds a few semantic hints (e.g., voice_catalog_id is 'preferred', the agent concept as a 'secretary'), but these are marginal and do not substantially supplement the schema. The baseline of 3 is appropriate given high coverage.

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 clearly states the action (create) and the resource (a KaiCalls agent) with a specific definition ('the secretary that answers this business’s calls'). It also names the endpoint it mirrors (POST /api/v1/agents) and enumerates the key configuration inputs (system prompt, greeting, voice, model), which distinguishes it from siblings like update_agent_config and list_agents.

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?

The description implies this is the creation tool by mentioning 'Every subsequent mutation to this agent is versioned' and referencing rollback_config and history tools, but it does not explicitly state when to use this vs. alternatives (e.g., 'use update_agent_config for existing agents'). The context is clear but the guidance is implicit rather than directive.

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