export_route

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

With no annotations, the description carries the full behavioral burden and does so well: it discloses that paths are returned for communication to the user, that vault_dir triggers side-copying into `<vault_dir>/Randos/<nom>/`, and that extra per-stage files are conditional on plan_stages. It omits overwrite/collision behavior and error handling, which are the notable gaps for a file-writing tool.

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?

The main action and return contract are front-loaded, then formats are enumerated as clean bullets. Structure is excellent; the per-format parentheticals are slightly verbose but each carries useful selection information.

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?

Even though an output schema exists, the description usefully clarifies that the tool returns file paths to relay to the user. For an export tool with no annotations, it covers outputs, format semantics, destination behavior, and a prerequisite; only overwrite/error behavior 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 0%, so the description must compensate. It documents two of three parameters thoroughly: each `formats` enum value is explained, and `vault_dir`'s side effect is described precisely. Only `route_id` is left implicit, though its meaning is self-evident from the name.

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 and resource in the first clause ('Écrit les fichiers d'un itinéraire et renvoie leurs chemins'), making the export operation unmistakable and clearly distinct from siblings like import_gpx. The per-format breakdown removes any ambiguity about what the tool produces.

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 gives clear context for selecting each format (gpx for watches/apps, md for Obsidian, html for interactive map, roadbook for printing) and notes the plan_stages prerequisite for `jour-N.gpx` files. It stops short of explicit when-not-to-use or naming alternative export paths, but the usage context is strong.

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