讀取某座標實際是什麼方塊

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint: false), so the description earns credit for enriching behavior beyond them: it discloses the implementation quirk (testforblock workaround because Education lacks a read command), the localized-name return semantics, and the failure contract (returns null plus raw message rather than guessing). It also warns that the message format is not officially guaranteed, which is exactly the kind of non-obvious behavior an agent needs.

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?

Four sentences, purpose front-loaded, and every sentence carries load: the core function, the implementation rationale, the return-type caveat plus sibling routing, and the failure/parsing behavior. It is on the longer side, but the length is justified because the tool's testforblock hack and unguaranteed message format are genuinely non-obvious and risk-mitigating for an agent.

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 an output schema, full safety annotations, and a clear single positional parameter, the description covers everything essential: purpose, alternative tool, output semantics caveat, and failure handling. Minor gaps remain — no mention of world-boundary/loaded-area constraints or permission requirements — but nothing an agent needs to invoke the tool correctly is missing.

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 reported at 0%, so the description carries the burden of parameter explanation, yet it says nothing about how to specify position, coordinate modes, or format. The gap is mitigated by the parameter being a self-evident coordinate triple and the schema's inline mode enum description (absolute/relative/local), making the missing compensation a moderate rather than severe deficiency.

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 uses a specific verb-resource pairing ('回報該座標實際上放著什麼' — reports what is actually at that coordinate) and immediately differentiates itself from siblings by warning that it returns localized display names, not block IDs, and explicitly routing ID-based checks to mc_test_block. The mechanism (air sentinel feeding testforblock) further clarifies what the tool is and is not.

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 explicit when-to-use context ('不需要你先猜' — use this when you need ground truth rather than assumptions) and an explicit when-not-to-use rule with a named alternative ('要用 ID 判斷請改用 mc_test_block'). It also states a concrete downstream constraint: the localized-name output cannot be fed back into mc_set_block.

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