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

The description uses 'List' which strongly implies a safe read-only operation, but annotations declare readOnlyHint: false and destructiveHint: true. This creates a dangerous contradiction where the agent might invoke a destructive operation believing it to be a harmless query.

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 consists of two efficiently structured sentences with zero redundancy; the first establishes the core function and the second provides usage guidance, delivering maximum information density with appropriate front-loading.

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 annotations indicate this is a destructive, non-read-only operation, the description fails to explain why a 'list' operation would modify or destroy data. This omission creates a critical gap for an operation that appears to be a simple query but behaves as a mutation.

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?

While the schema has 100% coverage documenting the 'state' parameter values ('want', 'read', 'dropped'), the description adds semantic context by mapping these technical states to user intents ('books they want to read', 'books they have read', etc.), helping the agent understand parameter semantics beyond raw enum values.

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 provides a specific verb (List), clear resource (bookmarked books), and filtering mechanism (bookmark state). It effectively distinguishes from siblings like save_bookmark (write vs. read) and explore_books (personal library vs. general discovery).

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 second sentence explicitly maps user intents ('reading list', 'books they want to read', etc.) to the tool's filtering capability, guiding invocation based on query context. However, it does not explicitly name alternative tools to avoid (e.g., when not to use this).

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