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

Annotations declare destructiveHint=true but the description supplies the operational specifics the agent actually needs: a security backup runs per site and a site without a verified backup is skipped, updates run sequentially in the background, and the response contains only batch_id plus scheduled/skipped lists with no results yet. It also discloses the chat-access confirmation round-trip where nothing is executed. This is substantial value beyond the annotations.

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 core purpose and the sibling alternative are front-loaded in the first clause, and nearly every sentence carries operational weight. It is dense and repeats the 20-item limit already encoded in the schema, which is the only clear waste.

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 destructive, open-world bulk mutation with no output schema, the description covers prerequisites, side effects (backup, per-site skip), execution model (background, sequential), return shape, confirmation flow, and the follow-up tool. Nothing an agent needs to invoke it correctly is missing.

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 the baseline is 3, but the description adds real semantics: items vs. alle_offenen are mutually exclusive, alle_offenen is read fresh at job time and capped at 20 per site with the remainder reported, and core is opt-in only. That goes beyond what the schema states, though the 'highest 20' cap slightly duplicates the schema's maxItems.

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 ('Startet EINEN Sammelauftrag für bis zu 25 WordPress-Sites') and explicitly contrasts it with the sibling it replaces ('statt viele einzelne update_wordpress_item-Aufrufe'). An agent can distinguish it from update_wordpress_item and get_bulk_update_status 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?

Gives explicit routing rules: use this instead of many single calls, call get_wordpress_overview beforehand, take slugs from get_outdated_plugins, use core only on explicit request, and do not poll afterwards unless the customer asks for progress. Negative guidance ('nicht von sich aus nachfragen') and tool alternatives are both named.

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