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

Annotations already declare non-read-only, non-idempotent, non-destructive. The description adds real context beyond them: cost/latency ('One LLM call') and the fact that it produces a fresh outline. But it does not state whether an existing draft/outline must already exist, whether the previous outline is overwritten, or any permission requirements.

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?

Three tight sentences, front-loaded with the pipeline role, followed by the required inputs and the return value. The parenthetical on `feedback` earns its space; only 'step 2 again' is slightly cryptic on first read.

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 11 parameters but 91% schema coverage and no output schema, the description supplies what the structured data cannot: the regeneration intent, the two key required inputs, the single-LLM-call cost, and the handoff to write_from_outline. It omits the role of `site`/`title` and the optional link/media flags, but those are covered by the schema.

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 91%, so the baseline is 3, and the description goes further by expanding what `feedback` should contain (sections to add, drop, reorder, tone), which the schema only labels as 'What to change about the outline'. It also clarifies why `prompt` is required (to keep the brief).

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+resource ('redo the outline', step 2 again) and places it in the Builder pipeline relative to the sibling that consumes its output (write_from_outline). It implies the contrast with the initial generate_outline via 'again', though it never names that sibling explicitly.

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 context for use: when you have `feedback` describing what to change, and instructs passing the original `prompt` to preserve the brief. It names the downstream consumer write_from_outline. It does not explicitly say when to prefer generate_outline (the first pass) over this tool.

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