preview_fix

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

With no annotations provided, the description carries the full burden. It discloses that the API replaces the full set, which is a key behavioral trait. However, it does not mention side effects, return values, or whether the tool is safe to invoke multiple times.

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 concise: two sentences, no wasted words. The first sentence states the purpose, and the second provides essential behavioral context. Information 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?

Given the tool is a preview tool with no output schema, the description should clarify what the preview entails (e.g., output format) and how to use it in conjunction with siblings. It lacks details on the return value or next steps after previewing.

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%, with only 'finding_index' having a description. The description does not add any parameter-level detail beyond what the schema provides. The 'project' parameter remains undocumented.

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 ('Describe') and resource ('proposed permission change for a finding'). It indicates the tool's role in previewing changes. However, it does not differentiate from sibling tools like 'audit_project' or 'list_findings'.

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 includes a critical guideline about outputting a complete replacement permission list due to API behavior. However, it does not explicitly state when to use this tool versus alternatives or when to avoid it.

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