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

With no annotations, the description carries full responsibility for behavioral disclosure. It does state 'safe, read-only' which covers safety, but doesn't specify what the request entails, whether any system permissions are needed, or what exactly the returned request looks like. It adds some value but remains incomplete for a tool that generates requests.

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, concise and front-loaded with the action and key qualifier ('safe, read-only'). It wastes no words, though it could be slightly more structured to separate the purpose from the behavior.

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 tool with 3 parameters, no output schema, and no annotations, the description is too sparse. It does not clarify parameter semantics (especially purpose and preferredMode), nor does it describe the output format of the request. The agent is left guessing at critical details, making it insufficient for reliable invocation.

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 0%, so the description must compensate. It mentions a 'named system' (likely the 'system' parameter) but does not explain 'purpose' or 'preferredMode' at all. The agent has no guidance on how to fill these fields beyond their names, which is insufficient.

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 clear verb ('return') and resource ('connection or export request'), and specifies the condition ('when an audit lacks evidence'). It hints at a read-only nature, but it doesn't explicitly differentiate from sibling tools like inspect_available_connections, which might seem similar.

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 provides a context ('when an audit lacks evidence') but does not explicitly state when not to use it or name alternatives like inspect_available_connections. It's implied that it's for filling evidence gaps, but an agent would benefit from explicit exclusions.

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