backfill_figure_text

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

With no annotations, the description carries the full burden and does so well: resumability, per-image commit boundaries, failure-requeue behavior, the 20/20 bound, and the guarantee that paid fallback is impossible. These are exactly the operational traits an agent needs before triggering a model-backed batch job.

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-loaded with the core behavior and the binding constraint before the arg list. The Args block largely mirrors the schema and could be trimmed, but each line carries a non-obvious detail.

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?

An output schema exists so return values need no prose, and for a bounded, resumable, mutation-style batch tool the description covers scope, safety, limits, and failure semantics sufficiently to call it correctly blind.

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 0%, so the description must compensate, and it does: note_paths are vault-relative, dry_run explicitly means no model calls or writes, and both limits are bounded 1-20. This adds real meaning over the bare schema types.

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?

Names a specific verb+resource ('Fill empty OCR/description fields') and pins the mechanism ('only the configured local VLM'), which cleanly separates it from siblings like extract_figures_for, reconcile_figures, and annotate_figure that also touch figures.

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?

It conveys the precondition (SB_VISION_BACKEND=local-only is mandatory) and the dry_run preview path, but never states explicitly when to reach for this tool over reconcile_figures or extract_figures_for, leaving the routing inference to the agent.

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