ptfx_merge

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

Annotations only say readOnlyHint=false and openWorldHint=false; the description goes well beyond by disclosing the exact output artifact ('<name>.ypt.xml (+ textures)'), the reference-vs-copy distinction for core textures, and the deterministic collision policy (numeric suffix on clashing rule names). These are precisely the side effects an agent needs before invoking a mutating tool.

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?

Purpose is front-loaded in the first clause, and every subsequent sentence carries real information — copy scope, texture reference behavior, collision handling, output files, next steps. It is dense and somewhat run-on, but there is no filler or restatement of the name.

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 file-writing tool with no output schema and nested (if not deeply) source objects, the description covers inputs-to-artifacts, side effects, and follow-up tools adequately. The remaining gap is the undocumented 'out_xml' override and whether/how the tool reports the created files, which matters for a tool that writes to disk.

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 33%, and the description compensates partially: it ties the required 'name' to the output filename and implies a default path, and it explains what 'sources' entries contribute. However, 'out_xml' is never explained anywhere, and the per-source 'rename' map and the '*' effects wildcard are left entirely to the schema, so meaning is still added unevenly.

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 and artifact ('Make a NEW dictionary from effects in other dictionaries') and immediately enumerates exactly what is copied: emitter rules, particle rules, chained effects, textures, model drawables. It also names the canonical source tool (ptfx_vanilla_search), so an agent can distinguish it from ptfx_edit and ptfx_pack without opening any schema.

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?

Gives clear workflow context — pull vanilla effects via ptfx_vanilla_search, then run ptfx_edit and ptfx_pack on the result — which positions the tool in a pipeline rather than leaving usage implicit. It lacks an explicit when-not-to-use statement (e.g. cloning a single effect vs a whole dictionary), which keeps it out of 5 territory.

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