tex_emat

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

With no annotations (readOnlyHint=false is default, no useful info), the description must carry the behavioral burden. It discloses that the tool writes files (writes .emat), that it depends on prior .edds imports, and that it reads .edds.meta GUIDs. However, it does not disclose the overwrite behavior, error conditions (e.g., missing .edds), or what happens on failure, though the overwrite parameter exists in schema.

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 a single dense paragraph of two sentences, which is reasonably economical. However, it mixes workflow context, technical mechanics, and parameter semantics in a compact run-on structure without clear separation. It is not front-loaded with the primary action verb; 'Phase 2' precedes the actual tool function, making the intent less immediately scannable.

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?

This is a file-writing (mutation) tool with no annotations and no output schema, operating within a complex multi-phase pipeline. The description should clarify prerequisites (that .edds must exist first), error states, and the overwrite behavior—none of which are covered. The 3 undocumented remaining parameters and the tool's role in a multi-step workflow leave the agent under-informed.

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%, so the description must compensate for 5 undocumented parameters. It partially does: family is explained (determines shader template), and it implies name/sub_path relate to file generation. But overwrite and addon_dir have zero explanation, and the description doesn't map which parameters are involved beyond family. The description adds some meaning but leaves gaps for 3+ parameters.

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 clearly states the tool writes .emat files ('Phase 2: .emat schreiben') after PNGs are imported to .edds by the workbench, reading GUIDs from .edds.meta and wiring real .edds references. The family parameter role is explained (determines shader template). While it lacks an explicit verb+resource target contrast with siblings, the purpose is specific and technical.

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 implies a sequential workflow ('Phase 2', 'nachdem die Workbench...') and states the family choices (metall/stoff/foliage). However, it does not explicitly contrast with sibling tools like tex_material or tex_generate, nor does it state when NOT to use this tool. The phase-ordering context is useful but not elaborated.

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