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

With no annotations, the description still discloses important behavior: no execution occurs, the scan would cost 15 credits, take 60-180 seconds, and report what gets saved. It does not clarify whether the preview itself consumes credits or exactly what 'saved' data will include.

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 three short sentences with the purpose and key constraint front-loaded. Every sentence adds useful information without filler.

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 preview tool with no annotations and no output schema, the description covers the core purpose and approval workflow. However, it leaves gaps around optional parameters, persistence behavior, and the exact saved-data semantics that an agent would need to invoke it confidently.

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 only 25%, with just the id parameter documented. The description does not explain persist, company_name, or company_website, so it does not compensate for the low schema coverage on the remaining parameters.

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 states a specific verb ('Show') and resource ('what deep_scan_agent would do'), and it scopes the preview to cost, duration, and what gets saved. The line 'Nothing runs' clearly distinguishes it from the actual deep_scan_agent sibling.

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?

It gives an explicit mandatory workflow: call this first and get the user's approval. It also names deep_scan_agent as the action being previewed, and 'Nothing runs' implicitly clarifies that this is not the execution tool.

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