Google Health Agent Manifest

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds value by confirming it does not call Google Health or expose secrets, providing important safety context beyond the structured annotations.

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 two sentences: first states what the tool provides, second states what it does not do. It's front-loaded with purpose and concise with no wasted words.

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?

The description gives the tool's purpose and safety guarantees, but omits guidance on parameter usage. Given that there is an output schema and two enum parameters, the description should explain the role of each parameter to be fully self-contained.

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 0%, and the description does not mention the two parameters ('client' and 'response_format') or their enums. The phrase 'client guidance' hints at the client parameter, but the description fails to explain what values do or how to choose them.

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 it provides 'install, runtime and client guidance' for AI agents, and explicitly says it does not call Google Health or expose secrets. This distinguishes it from sibling tools that operate on health data.

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 explains the tool's purpose and key exclusions (no external calls, no secrets), implying it should be used for setup/configuration guidance, not for data operations. However, it does not explicitly state when not to use it or provide alternatives.

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