fde_derive

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

With no annotations, the description carries the full burden. It discloses that it produces a machine draft requiring human confirmation and that it may emit a needsFullOntology prompt above a threshold. It also indicates that import is handled separately by ontology_import, implying no direct persist side effect. However, it does not specify the exact output format, whether the tool is read-only/write, or any permission/rate-limit context, leaving notable gaps.

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 a single, dense sentence that packs purpose, input, output, a workflow note, and a conditional. It is front-loaded with the main action and avoids fluff. The semicolon-separated structure is compact yet logically ordered, though a slightly more structured format could improve readability.

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 complexity (4 params, a nested array, no output schema), the description is incomplete. It states the output is a YAML draft and mentions the needsFullOntology threshold, but it does not describe the structure of the YAML (entities/concepts/relations fields), how the prompt is returned, or how the output should be handled when passed to ontology_import. The agent would need additional inference to correctly process the tool's return value.

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 has 100% description coverage, so the baseline is 3. The description's reference to '五要素' (five elements) and '访谈' (interview) maps to the elements and questions fields in the nodes array, but it adds little beyond what the schema already describes. It provides no additional nuance for enterprise_id or workflow_name.

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 states a specific action (ontology derivation) and resource (from five elements + interview to entity/concept/relation YAML draft). It identifies itself as 'engine four' in the FDE family, which distinguishes it from siblings like fde_interview, fde_classify, fde_distill, fde_deploy, and mentions the downstream ontology_import step, clarifying its role in the pipeline. However, it does not explicitly name a sibling tool to contrast with, so a perfect score is not warranted.

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 usage: it is used when you have interview data and five-elements to produce a YAML draft for manual review before ontology_import. It also mentions a conditional (prompting needsFullOntology when exceeding 10 entities or 5 nodes). However, it does not explicitly state when to use this tool instead of other FDE engines, nor does it provide exclusions or alternative conditions.

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