memoryguard_import_preview

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

With no annotations provided, the description carries the full behavioral burden. It explicitly discloses a key behavioral trait—'Read-only'—and indicates what the tool does ('detection + inventory'). It does not detail output structure or edge cases, but the core safety behavior is clearly communicated.

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 short, front-loaded sentences with no filler. It states the action, the resource, the formats, and the read-only nature efficiently.

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?

The description is adequate for tool selection and basic invocation, and the schema covers the parameters. However, there is no output schema, and the description does not clarify what the 'inventory' or 'detection' result looks like, which is reasonably important for a preview 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?

Schema description coverage is 100%, so the schema already documents both 'path' and 'workspace'. The description does not add meaningful parameter-level detail beyond the contextual note that bundles are ChatGPT/Claude/Gemini/Generic. Baseline 3 is appropriate.

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 uses a specific verb ('Preview') plus a clear resource ('offline import bundle') and names supported formats (ChatGPT/Claude/Gemini/Generic). The phrase 'Read-only detection + inventory' further clarifies it is a non-mutating inspection tool, distinguishing it from sibling import or extraction tools.

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 verb 'Preview' and 'Read-only' make the intended usage clear: inspect an offline bundle before committing to an import. It does not explicitly name alternative tools or state when not to use it, but the context is sufficient for an agent to infer the right use case.

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