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

Annotations already mark it read-only, idempotent and non-destructive, and the description adds real context beyond them: default ordering ('en cours d'abord') and, unusually for a tool with no output schema, the shape of the catalog result (a few editions or series with author, publisher, pages/volumes, language, cover_url). One tension: it queries an external national bibliography while openWorldHint is false, though the catalog is a fixed bounded dataset and this does not conflict with the read-only profile.

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?

One dense paragraph, front-loaded with the primary listing behavior before the conditional catalog mode. The parenthetical enumerations earn their place by defining scope, though packing two distinct behaviors into a single sentence makes it slightly heavier than necessary.

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 both modes, the ordering default, and the return shape despite having no output schema. Gaps are minor: no mention of pagination or result limits in listing mode, and no statement of whether type/status filters apply when searching the catalog.

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% and the enum descriptions already explain type and status values. The description still adds semantic value by explaining that catalog_title/catalog_author switch the tool into catalog-search mode rather than filtering the listing, and that the search is aimed at populating dandori_save_learning_item — a mode-level meaning the schema does not convey.

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 gives two specific verbs and their resources: listing readings/learnings (books, manga, comics, courses, podcasts…) and, when catalog_title is supplied, searching the BnF catalog. It enumerates the content kinds covered and names the downstream sibling (dandori_save_learning_item), so an agent can tell what this tool returns versus the other dandori_* tools.

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 clearly states the switch condition: without catalog_title it lists items (in-progress first), with catalog_title it searches the catalog instead of listing. That is explicit mode selection, but it gives no guidance on when to prefer this over sibling readers such as dandori_get_list_items, and no prerequisites or exclusion notes.

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