knowledge_add

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

With no annotations, the description carries the full burden and does so thoroughly: it discloses rejection behaviors (unknown parent_path, empty source, inconsistent norm fields, unknown occasion values), confirms nothing is written on validation failure, states that similar-node hints are never auto-merged, and even flags the self-reported/unverified nature of 'hook'/'selbst' triggers. This goes far beyond what annotations could supply.

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 content is dense and largely valuable, but it is delivered as one long unstructured paragraph with an embedded JSON example and a philosophical aside about why no default exists. It is front-loaded with the core purpose, but a structured format would make the many constraints easier to consume; not every sentence is strictly necessary.

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 21-parameter tool with no output schema and no annotations, the description covers an exceptional amount: required fields, validation, derivation, occasion semantics, similar-node hint behavior, and an end-to-end example. It is not a 5 because the general success return value is never described (only similar_node_hint is mentioned) and the anlass/occasion naming inconsistency creates ambiguity.

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 coverage is 90%, so the baseline is 3; the description adds meaningful cross-field semantics — the norm_entscheidung consistency rules, requirement that norm_entschieden_grund is mandatory, gilt_bis/gilt_ab ordering, and the example of a full valid payload. It loses a point because it refers to the schema's 'occasion' parameter as 'anlass', which could cause an agent to pass the wrong key.

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 first sentence states a specific action and resource — adding a new knowledge node to the tree — and the rest confirms this is a creation tool. It clearly distinguishes itself from siblings like knowledge_update, knowledge_read, and knowledge_relation_add without needing their schemas.

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?

It clearly frames when to call it (new node creation) and specifies strong preconditions: parent_path must exist or neuer_ast must be true, source must be non-empty, and norm_entscheidung/norm_entschieden_grund are mandatory with no default. It does not explicitly name sibling alternatives, so it falls short of a 5, but the context is much stronger than mere implication.

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