design_loop

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

Annotations declare readOnlyHint and idempotentHint, which the description is consistent with (it produces a draft rather than persisting anything). It goes beyond the annotations by enumerating the returned draft's contents (trigger, scope, one-round action, verifier, state files, stop conditions, budget, risk colors), the MVL sanity check, and nearest existing loops — though it does not say whether the draft is saved anywhere.

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?

Front-loads the core action and its precondition, then packs the return contents into a single dense clause, closing with the next-step instruction. Efficient overall, though the middle enumeration is long and slightly list-heavy.

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?

With no output schema, the description compensates by describing what the draft contains and what analysis accompanies it, and it states the required follow-up tool. Only the persistence/state question is left open, which is minor for a scaffolding tool.

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 documents goal, cadence, context, and constraints, and the baseline is 3. The description only loosely echoes these (bottleneck, domain, trigger) without adding format, syntax, or interaction detail beyond the schema.

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 (scaffold) and resource (a new loop spec), plus the trigger condition (from a stated bottleneck when no catalog loop fits). This distinguishes it cleanly from catalog-reading siblings like search_loops, get_loop, and pick_loop_for_goal.

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?

Explicitly scopes usage with 'when no catalog loop fits', implying the catalog tools are the alternative when one does fit, and names the required follow-up step (critique_loop on the completed draft). It stops short of naming a specific sibling to try first, so it is clear context without full routing.

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