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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, but the description adds substantial context beyond them: it describes the returned preview contents (method, full address with query, headers with credential hidden, and body), says it runs every check a real call does, notes that refusals happen here too, and mentions that it is free. This gives an agent a clear behavioral and safety model for the tool.

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 short and front-loaded, with the key distinction from connect_call stated immediately. The duplicated 'Free. Free.' at the end is a minor waste that keeps it from being maximally concise, but the rest of the text is efficient and purposeful.

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?

With no output schema, the description carries the burden of explaining return values, and it does so by listing the preview contents and noting that failed calls are refused here too. It also covers the core safety behavior via annotations and the preview-before-change workflow. The main missing piece is fuller explanation of the connection parameter and the exact failure output, which keeps it from being complete.

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 only 40%, so the description needs to compensate. It partly does by explaining that the preview includes the method, the full address with its query, headers, and body, which maps to several parameters. However, it does not explain the required connection parameter or the constraints on path, query, and method, leaving a meaningful gap in parameter understanding.

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 and resource — preview a call to a connected system — and immediately distinguishes it from the sibling connect_call by saying it returns exactly what connect_call would send without sending it. An agent can tell what this tool does and how it differs from the actual call tool without opening either schema.

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 explicitly names the alternative (connect_call) and gives a clear condition for using this tool: 'Show it to a person before a change.' That makes the intended preview-before-mutation workflow clear. It does not explicitly state when not to use it or any other exclusions, so it falls short of a full 5.

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