ygo_build_full_pipeline

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

No annotations are supplied, so the description carries the full burden, and it does disclose the most important behavioral fact: this is a write-heavy chain that ends by writing into the game folder ("slice the grid straight into the game folder"). It does not disclose overwrite semantics for the generated DB/scripts, what happens if an intermediate stage fails, or whether existing files in the target simulator directory are replaced. For a multi-stage mutation tool with zero annotation coverage, those are meaningful gaps.

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?

A single sentence with the pipeline stages front-loaded and zero filler; the optional step is flagged inline with "(optional)". Every clause conveys a distinct stage or condition, so nothing could be removed without losing information.

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 six-stage orchestrator with no annotations and no output schema, the description covers the stage sequence and the optional slicing well but omits the return value (paths, summary of generated artifacts) and failure/partial-completion behavior. An agent knows what the call does but not what it will get back or how to recover if a stage fails.

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 100%, so the schema already explains docxPath, gameRootDir, gridImagePath, and the simulatorProfile enum. The description adds only a small amount of meaning beyond that — that gridImagePath is used only for the optional slicing step and that the pipeline targets an archetype DOCX. Baseline 3 applies when the schema does the heavy lifting.

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 names a concrete verb and resource ("Run the whole archetype pipeline in one call") and enumerates every stage: read DOCX -> validate -> compile SQLite DB -> generate Lua scripts -> export ART_PROMPTS.md -> optional grid slicing. That makes it clearly distinguishable from the individual stage siblings (ygo_read_and_validate_docx, ygo_export_database_and_scripts, ygo_generate_art_prompts, ygo_slice_art_grid) because it is explicitly the aggregate. It stops short of 5 because it never names those siblings as the alternative path, leaving the contrast implicit.

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?

"In one call" and "(optional) slice the grid" imply the usage context: use this when you want the full chain, and slicing is conditional. However, there is no explicit when-to-use vs when-to-call-individual-steps guidance, no stated prerequisites (e.g. the DOCX must already exist), and no warning about when to prefer the granular tools for partial reruns. Usage is inferable but not spelled out.

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