Server status

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

Annotations already cover readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds real context: last_error is defined as the newest failure no later success has cleared, pauses are explained as a reaction to HKTVmall pushback, and check=true is disclosed as triggering a live order-history probe. The concrete precondition that shared connections need history permission is exactly the kind of operational caveat annotations cannot express.

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?

Length is reasonable and the most important signal (sign-in state) is front-loaded, but the prose is a run-on of parentheticals and fragments, e.g. "connection names whose HKTVmall account calls use (owner, shared)", which is grammatically broken and forces re-parsing. Much of the word budget is spent restating return fields that a declared output schema already covers.

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 a single optional parameter, full schema coverage, and an output schema, the description is complete enough to call correctly: it explains the only parameter's effect and its permission prerequisite. Given the output schema exists, the detailed field inventory is somewhat redundant, and the missing piece is when an agent should prefer this over just proceeding with a shopping call.

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 100% and the schema already says check runs the cached liveness canary, so the baseline would be 3. The description earns more by specifying what the canary actually does (an order-history probe) and what it requires (history permission on shared connections), which is meaningfully beyond the schema text.

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 enumerates exactly what the tool exposes: sign-in state, request budget, pause state, last_error, connection names/ownership, and connection_health. That is a specific and recognizable diagnostics/status resource, clearly distinct from the shopping-oriented siblings like hktv_get_cart or hktv_search. It loses a point because it never opens with a plain statement of the operation ("Returns server status...") and instead reads as a field dump, so the agent must infer the verb.

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 only implied: the sign-in/token/budget/pause fields signal "check here before calling other HKTVmall tools," and the check parameter text in the schema frames the canary as monitoring. There is no explicit when-to-use, when-not-to-use, or named alternative, and no guidance on when the extra canary call is worth its cost.

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