驗證「讀方塊」這條路還有效

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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds substantial behavioral context: it relies on testforblock failure message parsing, the failure mode is 'silent', it uses at most two commands, and guarantees no world writes. It also explains the algorithm (querying with bedrock to force a failure message if the cell is air), which is beyond what annotations provide. No contradiction with annotations.

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?

The description is dense and front-loaded with the core problem (failure message format instability), then explains the verification approach and the consequence of parseable=false. Each sentence earns its place, and the structure flows logically from problem to solution to implication. While it is longer than average, the complexity of the tool justifies the detail; minor redundancy with annotations (e.g., 'no writes to world') is acceptable for emphasis.

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?

The description covers the tool's purpose (why it exists), usage context (when to run it), internal behavior (how it works), and output interpretation (parseable=false implies protocol drift). Since an output schema exists, it does not need to enumerate return fields. No critical information is missing for an agent to select and invoke the tool correctly.

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 already documents the position object with x, y, z, and mode, including a description ('absolute=world coordinate; relative=~ relative to initiator; local=^ relative to facing') and a note that any coordinate works. Schema coverage is 100%, so the description does not need to add parameter semantics. The description adds no new param-level detail, so the baseline score of 3 is appropriate.

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 states a specific verb ('verifies') and a specific resource ('the parsing path for block reading'), making it clear this tool checks whether mc_read_block's results can be trusted. It distinguishes itself from sibling tools like mc_read_block and mc_test_block by framing itself as a probe of the underlying protocol, not a read operation itself. The title and description align perfectly, leaving no ambiguity about its role.

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 a clear trigger ('run before class') and a decision rule ('if parseable=false, mc_read_block results are untrustworthy'), indicating when to use this tool to validate the read path. It implies when it should be used instead of relying directly on mc_read_block, though it does not explicitly list exclusions or alternative tools. The context is strong but lacks explicit 'when-not-to-use' or sibling comparison.

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