get_detail

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

No annotations are provided, so the description carries the full burden, and it delivers: it discloses the data source (knowledge/detail_catalog.json), the three distinct return modes (overview, short list, complete detail with code/rules/parameters/status), the on-demand-only performance expectation, and the critical semantics of validated=false (not visually checked in Cadwork; code may be a placeholder). This is rich behavioral disclosure well beyond what the bare schema offers.

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 front-loaded with purpose and well structured using headings and code-block call patterns. It is long, but nearly every sentence earns its place given the catalog domain and three retrieval modes. The main inefficiency is that the 'Aufrufmuster' section and the 'Args' section partially restate the same parameter information, so a small redundancy keeps it from a perfect score.

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 3-parameter tool with an output schema and zero annotations, the description is nearly complete: it documents all parameters, return-mode differences, the validation flag, the source file, and usage timing. The one genuine gap is that all parameters are optional with empty-string defaults, yet the behavior of a bare get_detail() call (no args) is never specified — an agent could legitimately invoke it that way and get undefined behavior.

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 0% and there are no required parameters, so the description must fully compensate — and it does. Every parameter gets documented meaning: type with example values ('aw_decke', 'aw_ecke', 'aw_iw'), variant with examples ('platform', 'stumpf'), and list_types with its exact behavior ('True = nur Typen/Varianten-Übersicht zurückgeben'). The call-pattern section reinforces how combinations of parameters change the result.

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 opening sentence states a specific verb and resource: 'Liefert Konstruktionsdetails für den Holzrahmenbau (Detail-Katalog)' — a lookup tool for a timber-frame construction detail catalog. It further clarifies the domain with concrete examples of types and variants ('AW-Decken-Anschluss' with platform/setzschwelle/durchlaufend), and explicitly differentiates itself from the sibling execute_cadwork_command by stating it is NOT embedded there. An agent can tell exactly what this tool retrieves and how it differs from nearby tools.

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?

Provides explicit when-to-use guidance: 'Nur on-demand abrufen, wenn ein konkretes Detail gebaut werden soll' (only fetch on-demand when a concrete detail is to be built). It also gives a when-not/alternative signal by naming execute_cadwork_command and clarifying the tool is not part of its description. Three concrete call patterns (list_types=True, type only, type+variant) tell the agent exactly which invocation matches which need.

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