manage_materials

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

With no annotations, the description carries the full load and does substantial work: it discloses that 'set' is a mutation that must be saved afterwards, that Content Center/library parts are skipped, and what 'report' flags (Generic material, surface-only vendor models, missing mass). It stops short of stating failure behavior for bad material names or partial-application semantics.

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?

Structure is sensible: a short framing, per-action semantics, then an Args block that mostly adds examples rather than restating types. A few lines (the bare opening fragment) are thinner than they need to be, but there is little waste for an 8-parameter tool.

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?

Given eight parameters, no annotations, and an output schema that covers return shape, the description supplies the behavioral context an agent needs: what each action does, exclusions, and the save side effect. Remaining gaps (error handling, partial-failure behavior) are minor.

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 only 13%, so the description must compensate, and it largely does: it describes action values, `material` format with an example, `search` purpose, comma-separated `parts` patterns with an example, and the meaning of `only_generic`, `path`, and `only_problems`. The `instance` param is left to the schema (where it is documented), which is the only gap.

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 opening fragment is weak, but the per-action breakdown (report/list/set) makes clear this is a material management tool spanning inspection and assignment across many parts. It differentiates its three modes cleanly, though it never contrasts itself with sibling tools like edit_properties that might also touch materials.

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?

Each action carries implied selection criteria: 'report' to audit, 'list' to discover library names (with `search` narrowing), 'set' to assign. It also notes exclusions for 'set' (Content Center and library parts are left alone) and the need to save afterwards. No explicit when-not-to-use against a sibling, keeping it below a 5.

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