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

Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=true, destructiveHint=false, and the description adds genuine context beyond them: routed calls are 'scored, sealed, blocked if needed, and carry an AI-Decision-Receipt header'. That downstream behavior cannot be derived from the annotations. It does not, however, explain what state the call itself creates or why it is non-idempotent, so not a 5.

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, front-loaded with the core action and the returned artifacts, with no redundant restatement of the title. Some marketing-flavored phrasing ('scored, sealed, blocked') is slightly decorative, keeping it out of 5 territory.

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?

There is no output schema, so the description usefully names the two return artifacts (base URL and the stack-specific line). However, it leaves the undocumented 'label' parameter and the non-readonly/non-idempotent nature unexplained, so an agent cannot fully anticipate the call's side effects.

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 coverage is only 33% (just the 'stack' example), so the description must carry more weight. It implicitly covers api_key ('their sebbi.pro key') and stack ('the exact line to change for their stack'), but 'label' is never mentioned in either schema or description. Partial compensation for a low-coverage schema warrants a 3.

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+resource: routing the customer's OpenAI/Anthropic calls through sebbi.pro and returning a gateway base URL plus the exact line to change. This is far more concrete than a bare 'setup' label and lets an agent recognize it as a gateway-provisioning tool. It stops short of naming how it differs from the sibling sebbi_setup_advice, so it lands at 4 rather than 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?

Usage is implied by the purpose (use it when you want an app's traffic routed through sebbi.pro), but there is no explicit when-to-use, when-not-to-use, or reference to sebbi_setup_advice as the alternative. The only prerequisite hinted at is holding a sebbi.pro key. Adequate but the agent must infer the trigger condition.

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