create_authorization

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

Without annotations, the description carries the burden of behavioral disclosure, and it does a good job: it explains the prerequisite account/API-key setup, that the server must be restarted, and that user approval is required before confirmations can be sent. It does not detail every side effect or response, but the key behavioral expectations are clearly stated.

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 concise and well-structured, leading with the core action and purpose, then adding access requirements and a critical caveat. Every sentence serves a purpose, and there is no redundant or filler content.

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 9-parameter create tool with no output schema and no annotations, the description covers the essential context: what an authorization is, how approval works, and the access prerequisites. It does not describe return values or next steps after creation, but the schema handles parameter details and the approval lifecycle is sufficiently explained.

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 100%, so the baseline is 3. The description adds conceptual context like 'via a specific channel' and 'business name displayed to user,' which lightly reinforces channel and business_name, but it does not add meaningful parameter details beyond the schema.

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 action ('Create a new authorization request') and clearly defines the resource: authorizations grant permission to send confirmations via a channel. It also distinguishes itself from confirmation creation by noting the user must approve before confirmations can be sent, which separates it from sibling tools like create_confirmation.

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 gives useful setup context (requires a Proof account, API key, server restart) and implies when the tool should be used, but it does not explicitly name alternatives or state when to choose this over related authorization tools. The 'start_login does NOT open this tool' note is an exclusion, but it is more about environment setup than tool selection.

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