record_extraction

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

Annotations already declare the safety profile (not read-only, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real behavioural context beyond them: writes are versioned in the graph, and the call returns canonical-task suggestions used for deduplication. It does not say how conflicts or duplicates are merged, which keeps it from a 5.

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 short sentences, no filler. The write action and its versioned nature come first, and the return-value side effect follows. Every clause carries information an agent cannot get from the structured fields.

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?

An output schema exists, so return values need not be explained, and annotations cover the safety profile; the description supplies the remaining essentials (what is stored, that it is versioned, provenance via quelle, dedup suggestions). A brief note on how re-recording the same extraction is handled (beyond idempotentHint) would make it complete.

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 schema already documents bezug, quelle, skills, aufgaben and automatisierungen in detail. The description adds no extra semantics about parameter formats or interactions (e.g. how a kanonisch ID affects deduplication). Baseline 3 applies when the schema does the heavy lifting.

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 (versioniert im Graphen speichern) and enumerates the exact resources written: Aufgaben, Skills, Automatisierungsbewertungen. It also names a secondary effect (returning canonical task suggestions for deduplication), which makes the tool's role distinct. It does not explicitly contrast itself with near neighbours like remember or import_reference_data, so it stops short of a 5.

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 phrase 'vom Modell oder von Fachexperten extrahiert' implies the usage context (recording an extraction result, with the quelle parameter distinguishing LLM vs expert provenance), but there is no explicit when-to-use/when-not statement and no pointer to alternatives such as remember or import_reference_data. Usage is inferable but not spelled out.

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