material_apply

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

Annotations already declare readOnly=false, destructive=false, idempotent=false, openWorld=false, so the description need not restate safety. But it adds almost nothing beyond them: it does not explain the optimistic-concurrency contract implied by expected_revision/map_epoch, what happens on a revision mismatch, whether the write is undoable, or that existing material in the region is overwritten. The only extra hint is "aligned".

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?

It is a single front-loaded sentence with no filler, which is good. But brevity here reads as under-specification rather than precision, given a five-parameter mutation with concurrency tokens.

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?

For a destructive-capable write with no output schema and zero parameter documentation, the description leaves an agent without enough information to call it safely: no explanation of epochs/revisions, selection alignment rules, or result/error behavior.

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 0% across five required parameters, so the description carries the full burden and largely fails. It offers no meaning for request_id, map_epoch, expected_revision, or the origin/count/grid/orient selection structure, and only obliquely hints that the selection must be aligned.

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?

It names a verb ("Apply") and a resource ("material") plus a target ("selection"), so the general action is graspable and distinguishable from texture_apply. However, "built-in volume/clip material" does not match the actual enum, which includes air, water, lava, glass, and death, and "aligned selection" is undefined, leaving the exact scope fuzzy.

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?

There is no statement of when to use this versus texture_apply or geometry_fill, no prerequisites (e.g., that the selection must be grid-aligned or that the map must be open), and no conditions under which it should not be called.

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