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

Annotations only indicate readOnlyHint=false and destructiveHint=false, which are generic. The description adds valuable behavioral details: it requires the 'config' scope and Founder tier, and it reveals a domain-specific rule about social channels always requiring human review. This goes well beyond the annotations, providing the agent with essential operational context.

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 three sentences long, with the core purpose in the first sentence, followed by prerequisites and a crucial exception. Every sentence carries meaningful, non-redundant information, making it compact and well-structured.

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 simple two-parameter setter with no output schema, the description is largely complete. It covers the main action, required permissions, and a key limitation. It lacks explicit mention of return values or error behavior, but these are generally less critical for a configuration setter and the description already provides the key context an agent needs.

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 50% (loop_type is described, level only has enum). The description clarifies the meaning of the 'level' parameter by listing the acceptable values in context ('review, one_click or autonomous') and adds the cross-parameter constraint regarding social channels. It doesn't fully explain each level's behavior, but it sufficiently compensates for the missing schema description on 'level'.

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 tool's function: setting the autonomy level of a growth marketing loop, and explicitly lists the three possible levels (review, one_click, autonomous). This verb+resource+scope combination effectively distinguishes it from sibling tools like set_loop_cadence or run_loop.

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?

Provides clear context including required scope and tier, and a critical constraint about social/distribution channels never accepting 'autonomous'. However, it doesn't explicitly name alternative tools or when to use them over this one, so it falls short of a perfect score.

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