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

Annotations already indicate read-only and idempotent behavior. The description adds valuable behavioral context by explaining the conditional return: full-text passage with an ID, or a table of contents (with ID, section, and title) without one. This goes beyond safety hints and clarifies output expectations, though it does not discuss errors, pagination, or auth requirements.

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 description is two sentences, front-loaded with the primary purpose, and covers both usage modes without redundant words. Every sentence contributes meaningful information, making it an excellent example of concise, structured documentation.

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?

Given the tool's simplicity—one optional parameter, no output schema, and rich annotations—the description fully covers all necessary aspects. It explains both invocation modes, the content of the response, and its relationship to the search tool. No critical information is missing for an agent to use 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?

The schema describes 'id' as the passage identifier with an example, achieving 100% coverage. The description adds provenance by stating the ID comes from "website_durchsuchen", which is not in the schema and helps the agent understand where to obtain valid values. This additional context elevates the semantics above the schema baseline.

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?

The description clearly states the tool's function: "Liefert eine Passage der Website im Volltext" (delivers a full-text passage), and it distinguishes itself from siblings by referencing the ID from "website_durchsuchen". The no-ID case (returning a table of contents) is also explicitly described, leaving no ambiguity.

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?

The description provides explicit guidance: use the ID from "website_durchsuchen" to retrieve a specific passage, or omit the ID to get an overview. This establishes the prerequisite workflow and clearly defines when each mode is appropriate, which is more explicit than just stating the tool exists.

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