get_settings

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

Annotations already declare readOnlyHint=true, but the description goes well beyond: it discloses that the webhook signing secret is never returned to an API key, that webhook.secret_set is reported instead, and where the actual value can be seen. That is meaningful return-shape and security behavior an agent cannot infer from the annotation.

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?

Front-loaded with what is returned, then alternatives, then security caveat, then access prerequisites — a logical order. Each sentence carries non-redundant information, though the block is a touch long for a zero-argument getter; nothing is truly wasted but the access note is slightly verbose.

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 must carry return-value burden, and it does — listing the webhook endpoint, its event subscriptions, the default proof lifetime, and the secret_set surrogate. It stops short of describing the full response envelope, but for a settings getter the key fields are covered.

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?

The input schema is an empty object with zero parameters, so there are no parameter semantics to document; per the rubric a 0-param tool baselines at 4. The description correctly adds no parameter noise, and schemas add nothing an agent would miss.

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?

Opens with a specific verb+resource ('Get account settings') and then enumerates exactly which settings — the outbound webhook endpoint with its event subscriptions and the default proof lifetime. It explicitly separates what it does NOT cover (branding, which is per sub-account) and names the sibling that covers it, so an agent can distinguish it from get_profile without opening schemas.

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?

Explicitly routes branding reads to get_profile and points to update_settings for the rotated secret, giving named alternatives with the conditions that select them. The ACCESS block adds the prerequisite (Proof account, PROOF_API_KEY, restart) and explicitly warns that start_login does NOT open this tool, closing a common dead-end.

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