Fallback writer: generate the piece deterministically

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

With no annotations, the description carries the full load and delivers: deterministic assembly, verbatim quote spans with transcript timestamps, save-only-if-citation-check-passes, transcript never edited to fit a piece, and idempotent regeneration. These are exactly the behavioral traits an agent needs before invoking it.

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 crucial routing word FALLBACK in caps, then layers usage, mechanics, and next step in four tight sentences. Slightly dense but every sentence carries distinct information; no filler.

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?

Covers purpose, routing, output ordering, citation gating, and follow-up tool despite having no annotations or output schema. An agent has everything needed to decide whether and how to call it.

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?

Only one parameter (brief_id) and schema description coverage is 100%, so the schema already documents it. The description adds only the implication that the brief's transcript is what gets written up; it adds no syntax or selection nuance beyond the schema. Baseline 3 applies.

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?

Explicitly names itself as the FALLBACK writer for deterministic assembly of the case study from the saved transcript, and states the output order (story, quotes, per-question answers). This makes it clearly distinguishable from the sibling draft_piece, which is the host-written path.

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 an explicit when-to-use condition (only when no host is writing, e.g. `npm run spine`) and a when-not/preferred-alternative (inside Claude, use draft_piece then check_citations). It even names the next step, check_citations.

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