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

Adds real behavioural facts beyond readOnlyHint/openWorldHint: Strapi always returns the entire media library and page/page_size/ids are applied afterwards, and _meta.total is the count after the ids filter — a non-obvious performance and counting caveat an agent would otherwise get wrong. It also discloses the workspace-optional-when-single-workspace rule, which no annotation covers.

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 purpose and pagination caveat, then the full/ids recipe, then the workspace note — a sensible ordering with little waste. The enumeration of returned fields ({id, documentId, name, url, mime, size_kb, ...}) is somewhat redundant given an output schema exists, which keeps it from a 5.

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?

For a paginated read over an external CMS whose schema has no field descriptions, the definition covers return shape, filtering semantics, pagination ordering, and workspace resolution. Combined with the output schema and read-only annotation, an agent has everything needed to call it correctly.

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?

With 0% schema description coverage the description must carry the parameter burden, and it does: it defines the compact row shape for the default (full=False) versus the full file objects, explains ids as numeric file ids applied as a filter, and explains that page/page_size act on the post-filter list. workspace is covered with its slug and optionality. Nothing in the 5-param schema is left unexplained.

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 ("Dateien aus der Strapi-Medienbibliothek auflisten (paginiert)") and immediately clarifies the shape of what comes back. It is clearly distinguishable from unrelated list tools by the Strapi media-library scope, but it never names the near-neighbours (wp_list_media, gbp_list_media, strapi_get_entry) a router might confuse it with.

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 a concrete usage recipe: "der übliche Weg, um für ein oder zwei Bilder das komplette File-Objekt zu holen: strapi_list_media(ids=[42], full=True)", plus when full=True is needed (image nodes in Blocks rich-text fields). It stops short of saying when NOT to use it or which sibling to pick instead, so it is clear context rather than full routing guidance.

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