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

Annotations only say non-readOnly, non-destructive, open-world; the description adds substantive behavior: drafts are invisible until a separate deliberate publish, locale silently falls back to default when omitted for localized content types, missing full file objects in Blocks rich text yield 400 ValidationError, and __component is auto-reordered to avoid 'Invalid key __component'. These are exactly the failure modes an agent would otherwise hit.

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 key fact (DRAFT, not public) is front-loaded and the dash-led paragraphs keep dense rules scannable. It is nonetheless long, and the landingpage section (Hero, Nutzen, FAQ, image sourcing) reads as editorial workflow guidance that could live in a prompt or sibling doc rather than a tool definition.

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 4-param mutation with nested free-form data, the description covers prerequisites (media IDs, full file objects), pitfalls (400s on __component and rich-text images), locale defaults, and the follow-up read pattern. An output schema exists, so response shape legitimately needn't be described.

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 carry the load and does: data is the field-value object sent internally as {"data": ...}, locale selects the i18n version, workspace is the customer slug and optional for single-workspace setups, and collection is constrained (letters/digits/_/-, no plugin routes like users/upload/admin, else error invalid_collection). All four parameters gain meaning the schema does not provide.

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 ('einen neuen Strapi-Eintrag als DRAFT anlegen') and immediately scopes it: the entry is NOT public until strapi_publish_entry. That contrast with the publish sibling lets an agent place the tool without opening any 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?

Names explicit alternatives and the conditions selecting them: use strapi_publish_entry for going live, strapi_get_entry(..., status='draft') to read back (noting v5 returns 404 without that status), and read strapi_list_entries/strapi_get_entry first when building landingpages. It also states when to ask the user for images rather than reusing foreign ones.

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