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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds the underlying endpoint (GET /servers) but says nothing about pagination behavior, default page size, or result volume — the main behavioral facts an agent needs for a paginated list call.

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?

Two tight sentences: scope and filters first, endpoint last. Nothing is redundant or buried, and every clause carries information.

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 read-only list tool with full schema coverage and no output schema, the description is nearly sufficient. The one real gap is pagination: page/per_page exist in the schema but the description never notes that results are paged or how to iterate.

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 description coverage is 100%, so every parameter (name, page, per_page, status, label_selector) is already documented in the schema. The description merely echoes the filter trio and adds no semantics beyond it, which is the baseline-3 case.

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 ("List the servers") and scopes it to "the token's project." The plural/singular contrast with sibling hetzner_get_server is inferable, but the description never explicitly names that sibling or the list_* peers to sharpen the boundary.

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?

"Optionally filtered by name, status or a label selector" implies when the filters are useful, but there is no explicit when-to-use vs. hetzner_get_server, no guidance on when filtering is better than fetching everything, and no mention of how pagination should be driven.

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