preview_write

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds the key behavioral trait 'without executing it,' which aligns with annotations but does not provide additional details like authorization needs or rate limits. This is adequate given the annotation coverage.

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 a single sentence that is front-loaded and contains no unnecessary words. Every element serves a purpose, making it highly concise.

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?

Despite having an output schema (not shown), the description lacks guidance on parameter usage and return values. With 7 parameters and no schema descriptions, the description is insufficient for correct tool invocation, especially for an agent unfamiliar with the tool.

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?

The input schema has 7 parameters with 0% schema description coverage, and the tool description provides no explanation of any parameter. Without compensating information, the agent cannot understand the meaning or proper usage of parameters like 'model,' 'operation,' 'values,' etc.

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 "Preview create, write, or unlink without executing it" clearly states the tool's purpose with a specific verb ('preview') and resource scope ('create, write, or unlink'). It distinguishes itself from sibling tools like 'execute_approved_write' and 'validate_write' that perform actual execution or validation.

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 implies usage: when you want to see the effect of a write operation without committing. It is clear from the context, but it does not explicitly mention alternatives or when not to use this tool, which would make it a 5.

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