Learning path

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds genuinely new behavior: fixed ordering (starter courses first), a hard page size of 20, and URL tolerance for the slug. It stops short of describing failure behavior for an invalid or expired slug.

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 short blocks, front-loaded with the payload contents, then the required input provenance, then pagination and the follow-up call. The Persian gloss '(مسیر یادگیری)' is the only optional token and it aids disambiguation for a multilingual site.

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 no output schema, the description carries the burden of describing the return value, and it does so (ordered courses, totals, related paths). Combined with the sibling pointer and pagination rules, an agent can call this correctly on the first try; only edge-case behavior for bad slugs 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 still adds meaning beyond the schema: it explains where `slug` originates, that a URL variant is accepted, and that `page` is tied to a 20-item page size. It does not clarify what happens past the last page or how the 500-page maximum behaves.

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?

Opens with a specific verb and resource ('Get one Faradars learning path') and immediately enumerates what the response contains: ordered course list, totals, related paths. The word 'one' plus the sibling name fr_learning_paths makes the singular-vs-list distinction unmistakable.

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 explicit prerequisites and provenance ('slug comes from fr_learning_paths'), an acceptable alternative input (a how-to-learn URL), and an explicit next step ('Then call fr_course on a course'). Pagination guidance ('20 per page; use page for more') tells the agent exactly when to iterate.

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