snw_create_derived_property

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

With no annotations provided, the description carries the burden of behavioral disclosure. It mentions that the property is read-only and that persistence occurs, but it does not disclose potential side effects (e.g., dependencies, resource usage) or the fact that replacing requires explicit flag. It also does not explain what happens on failure. This is adequate but not comprehensive.

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 exceptionally short, which is good for conciseness, but it may be too sparse given the tool's complexity. The single sentence is front-loaded with the core action, and the replacement note is placed at the end. However, for a tool with nested objects and multiple params, more detail could be helpful without being verbose.

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?

Despite having an output schema, the description is extremely incomplete for a complex creation tool. It lacks any guidance on the required parameters (like plan, plan_digest, ontology_version), what constitutes a valid plan, or how to construct it. The 0% schema coverage means agents are left without understanding the core inputs, making this definition inadequate.

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 the schema is complex (requires understanding of SemanticJoinPlan, LinkHop, etc.). The description does not explain the parameters beyond hinting at replace_existing, leaving most parameter semantics (e.g., what plan_digest is, how plan is structured) unclear. The description fails to compensate for the lack of schema documentation.

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 persists a read-only derived property, which is a specific verb-resource combination. It also highlights the key requirement for replacement. However, it does not explicitly contrast with siblings like snw_execute_derived_property, though the sibling list suggests it is for creation.

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 implies the tool is for persisting derived properties, and the note about replacement with replace_existing provides usage context. It does not explicitly state when not to use it or mention alternatives, but the sibling names suggest creation vs execution distinction. This is clear enough for an agent to infer usage.

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