create_sd_targets

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

With no annotations provided, the description carries the full burden. It correctly labels the tool as 'guarded write' and discloses that this local server is an introspection stub, meaning writes are not performed locally. This is a key behavioral trait. However, it does not elaborate on guard details or return behavior.

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 long, front-loading the purpose and key behavioral notes. No extraneous content.

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?

Given the absence of an output schema and annotations, the description should provide more context about the guarded write flow, especially how preview differs from actual creation. The 'changes' parameter is vaguely described as 'High-level desired changes' without examples or constraints. Adequate but with gaps.

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%, with each parameter having a description in the schema. The tool description adds no further details beyond what the schema already provides for parameters like 'preview', 'dry_run', 'changes', etc. The baseline for high coverage is 3.

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 verb actions ('Preview or create') and the specific resource ('Sponsored Display targets'). It distinguishes from sibling tools like create_sd_campaigns by targeting a different entity. The addition of '[Ads / guarded write]' and the stub clarification further refine the purpose.

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 indicates when to use the tool (for preview or creation of SD targets) and notes that it's a local stub for a hosted endpoint. However, it does not explicitly state when not to use it or compare it with alternatives such as update_sd_target_state or archive_sd_targets.

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