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

Annotations already establish the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), so the description's burden is lighter. It adds useful behavioral detail about what is returned (whether a human typed live, and when), but says nothing about code validity, expiry, or error behavior for bad codes.

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?

A single front-loaded sentence that states the resource, its format, and the returned facts with no padding or redundancy.

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 correctly summarizes the return fields (human-typed, live, timestamp) and the required input format — enough for an agent to call it. Minor gaps remain around invalid-code behavior and how results are keyed.

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 0%, so the description must compensate for the single undocumented parameter — and it does by giving the expected format HK-XXXX-XXXX. It stops short of stating whether the code is case-sensitive or accepted in other formats.

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 ("Look up") and resource ("a Human Keys code") with the concrete code format HK-XXXX-XXXX, so the agent knows exactly what is being fetched. It doesn't differentiate itself from sibling lookups like sebbi_verify_chain or sebbi_forever_proof, so it stops short of 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 description implies the use case (checking whether a human typed text) but never says when to choose this over the sibling proof/verify tools or what prerequisites apply. Usage is inferable but not stated.

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