Scaffold a teaching companion pack from a COMP

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

The description discloses behaviors beyond annotations: it writes files to vault (consistent with readOnlyHint=false), captures topology for reference only (not installable recipe), and composes read-only bridge calls. It adds context about output files and post-usage editing by the artist. No contradiction with annotations (although destructiveHint=false, writing files is considered non-destructive custom when composition is read-only).

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 concise, using about five sentences to convey purpose, outputs, and constraints. It front-loads the action with a clear verb ('Build a teaching/selling companion'). Every sentence adds value, though it could possibly be shortened slightly without losing meaning.

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 the complexity (8 parameters, multiple file outputs, no output schema), the description adequately covers what the tool does, where it writes, and what prerequisites are needed (vault path, running bridge). It also clarifies what the output is not (RecipeSchema-compatible). It lacks a statement about the return value or success indication, but the file outputs serve as implicit response.

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?

The input schema covers 75% of parameters with descriptions. The description mentions 'snapshot the COMP's topology' and 'scaffold an N-step lesson plan', which relates to source_comp and lesson_count respectively, but does not add new semantic meaning beyond the schema's descriptions. Baseline of 3 is appropriate given high schema coverage.

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 it scaffolds a teaching companion pack for a network, specifying the exact outputs (tutorial.md, topology.json, etc.) and actions (snapshot topology, capture previews, scaffold lesson plan). It distinguishes from sibling tools like create_macro or scaffold_recipe_template by emphasizing read-only composition and the result not being a RecipeSchema-compatible installable recipe.

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 provides context (builds companion for network, requires vault path and running TouchDesigner bridge) but does not explicitly state when to use this tool over alternatives or when not to use it. The mention 'Composes existing read-only bridge calls — the artist edits the lesson body afterwards' implies a non-destructive, preparatory role, but no direct comparison to siblings.

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