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

Annotations already declare readOnlyHint and openWorldHint, yet the description adds real behavioral context: v5 returns only published entries by default, drafts need status='draft', that status only takes effect on v5, populate='*' is one level deep, and an invalid collection yields {"error":"invalid_collection"}. Pagination behavior (page/page_size semantics and caps) is not described beyond the word 'paginiert'.

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?

Purpose and pagination come first, then each parameter is annotated in a compact clause with an inline example, and the constraints (invalid_collection error, v4/v5 divergence) are folded into the same flow. Dense but every sentence adds information an agent needs.

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 an output schema present, return values needn't be explained, and the description covers collection/filters/populate/sort/locale/status/workspace thoroughly including version-specific traps. The remaining gap is pagination (page, page_size defaults and limits), which an agent would have to infer from the schema defaults alone.

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 all parameter meaning, and it does for most: collection format restrictions, filters as a nested Strapi filter dict with an example, populate variants ('*', 'cover', nested dict), sort ('createdAt:desc'), locale (v5 i18n, 'de'), status values, workspace slug. The two pagination parameters page and page_size are left entirely to their bare schema defaults (1 and 25), so the compensation is strong but incomplete.

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 ('Einträge einer Strapi-Collection auflisten') plus scope ('paginiert'), which separates it cleanly from strapi_get_entry, strapi_create_entry and strapi_delete_entry. It even routes to strapi_get_entry for populate details, so an agent can place it in the CRUD family without opening a 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?

Gives clear conditional guidance: status='draft' is required to see drafts on Strapi v5, drafts are unreachable on v4, plugin routes like users/upload/admin are invalid, and workspace may be omitted when only one workspace exists. It lacks an explicit 'use X instead when you want a single entry' routing statement, so it stops short of full alternative coverage.

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