Gateway Approve (Deprecated)

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false. The description adds the meaningful behavioral concept that approval is separated from execution (two-phase), which the annotations do not convey. It does not disclose auth/scope requirements for a valid approval, what state the approval leaves behind, or the migration path beyond the deprecation string.

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?

Two compact sentences, front-loaded with the deprecation notice and then the core semantics. Every clause carries information; the only weakness is that the extreme brevity comes at the cost of parameter and lifecycle detail.

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 5-parameter, 0%-coverage tool with no output schema, the description omits parameter meaning, scope/auth prerequisites and post-approval state. Even accounting for deprecation reducing the need for detail, an agent cannot correctly populate the required inputs from this text.

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% across five parameters (agentId, tool, params, context, scopeRequired) with a nested free-form params object, yet the description documents none of them. It provides no added meaning over the bare schema, leaving required inputs like scopeRequired entirely undefined.

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?

States a specific verb (approve) and resource (a tool call) with clear scope, and the 'two-phase execution ... without executing it' phrasing distinguishes it from the executing sibling gateway_process_tool_call. The deprecation tag additionally tells the agent the tool is sunset. It stops short of naming the sibling that replaces it, keeping it from a 5.

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 phrase 'approve a tool call without executing it' implies the usage context (decouple approval from execution, unlike gateway_process_tool_call), but never states when to pick this over the executing path or what the approval lifecycle requires. The deprecation notice usefully says when NOT to use it, but no explicit alternative beyond a bare REST URL.

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