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

The annotations already indicate this is a non-destructive, idempotent write operation. The description adds useful behavioral context beyond that: favorites affect scheduling priority and can be filtered via list_keywords favorites_only. This helps the agent understand the downstream effects of setting a favorite.

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?

Three concise sentences, each serving a purpose: the action, the behavioral consequence, and the conditional parameter guidance. No filler or redundant detail; the most important action is front-loaded.

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 mutation tool, the description covers the action, related list_keywords filtering, account-with-multiple-websites handling, and relevant data sources. The output schema handles return-value expectations, so nothing critical is missing.

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 the schema fully documents keyword_id, website_id, and is_favorite. The description mostly restates the website_id condition already present in the schema, adding minimal new parameter-level meaning.

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 opens with a specific verb and resource ('Stars or unstars a keyword') and clarifies the feature's role in auto-selection and filtering. This clearly distinguishes it from siblings like list_keywords or add_keywords.

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 provides clear context for when this tool is relevant: favorites are scheduled first and can be filtered with list_keywords favorites_only. It also instructs when to pass website_id. It does not explicitly state when not to use it or name an alternative, but the usage context is strong.

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