export_markdown

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

Despite annotations already declaring idempotency and non-destructiveness, the description adds substantive behavior beyond them: it preserves `exported_at` on unchanged sources, emits `INDEX.md` + `.manifest.json`, and deletes `.md` files for sources that no longer exist. Surfacing that stale-file cleanup is exactly the kind of side effect an agent needs but would not infer from annotations.

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 export target, then structured by mode with parenthetical modifiers, so no sentence is filler. It is dense and somewhat long, but the density is earned by the amount of mode-specific behavior being conveyed.

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 an output schema present, the description needn't cover return values, and it still accounts for both modes, incremental vs. forced behavior, destination selection, and the stale-file cleanup that would otherwise be a surprise. Nothing needed to invoke it correctly is missing.

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 100%, so the baseline is 3, but the description goes further by framing `force` and `refresh` in terms of which mode they apply to ('Notebook completo' vs. 'Una fuente'), which the schema's per-property text does not make as clear cross-parameter-wise. `directory` destination semantics are covered by both schema and prose.

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 opens with a specific verb and resource ('Exporta a `.md` (con front matter)') and immediately splits the two operating modes: full notebook vs. single source. That distinction, plus the mention of front matter and produced artifacts, lets an agent tell exactly what the tool produces without opening the schema.

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 explains both invocation modes and the conditions that select each modifier ('incremental', '`force` reescribe todo', 'con `refresh`, lo vuelve a descargar antes'). It stops short of naming when an agent should prefer this over other retrieval siblings, but no sibling competes for the same output, so the guidance is clear in context.

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