gateway_access_request_create

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

Annotations carry only a title, so the description bears the full burden. It adds one valuable behavioral disclosure — 'This never grants access automatically' — preventing the costly assumption that the request results in access. But it omits other relevant behavior, such as the request entering an approval workflow or the semantics of idempotency_key and ttl_days.

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 sentences with zero filler; the core action is front-loaded and the critical caveat ('never grants access automatically') follows immediately. Every word earns its place.

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 output schema covers return values, but the description is still incomplete for a workflow-creating tool with four undocumented parameters. It does not place the tool in its lifecycle context: what happens after submission, whether later cancellation is needed, or how this request relates to the approval/decide sibling tools. An agent can select the tool but cannot invoke it with full confidence or set correct user expectations.

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, but it only indirectly glosses package_key ('business access package'). The required parameters (package_key, reason) get no explicit explanation, and ttl_days and idempotency_key are entirely unaddressed, leaving important invocation details to inference.

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 ('Request'), resource ('versioned business access package'), and actor ('current user'), clearly differentiating it from siblings like gateway_admin_grant_access_package (granting) and gateway_admin_access_request_decide (deciding on requests). An agent can tell what this does at a glance.

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 implies scope ('for the current user') and gives a when-not signal ('never grants access automatically'), which tells the agent this tool will not deliver immediate access. However, it never names alternative tools (e.g., gateway_admin_grant_access_package) or states explicit conditions for choosing them instead.

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