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

Annotations already declare destructiveHint=true, but the description adds genuinely useful context beyond that: attached blocks are preserved unless with_attached is set, and blocks in restricted zones are skipped. This tells the agent exactly what survives a destructive call, which 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?

Three short sentences, front-loaded with the core action and no wasted filler. The second sentence's grammar is awkward ('Those something hangs on stay'), which slightly hurts readability, but the content is tightly packed.

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?

Covers the destructive semantics and exceptions well for a mutation tool, but there is no output schema and no indication of what is returned (e.g., count of removed blocks) or permission/ownership requirements. Adequate but leaves the agent guessing about results and access.

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 75%, with rows/columns/layers already documented as '[from, to], or [one]'. The description compensates for the single undocumented parameter by explaining with_attached's semantics (also removes blocks attached to the ones removed), which the schema does not convey.

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 ('takes out') and resource ('blocks'), and is distinguishable from siblings like place_blocks, look_blocks, and remove_object. However, 'in a box' is never defined — the agent must infer it means the rows/columns/layers region, and the colloquial phrasing leaves the operation's actual scope ambiguous.

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?

No guidance on when to use this versus remove_object, place_blocks, or look_blocks, and no stated preconditions or context. The description only describes internal behavior rules (attached blocks, restricted zones), not when this tool is the right choice.

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