propose_canon_facts

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

Annotations declare readOnlyHint=true, and description confirms it does not commit (コミットしない). It discloses return structure (high_new, low_new, existing, summary) and notes it does not fold into story types (LIFE/RANK).

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 dense and contains rich information but is somewhat verbose and stream-of-consciousness. It front-loads the purpose but could be more organized and concise.

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, no output schema) and readOnly annotation, the description covers return values, usage flow, and fine-grained behavior. It does not cover error conditions or length limits, but for the intended narrative use it is adequate.

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 0% and description provides no explanation for the 4 parameters (branch, chapter, chapter_text, pov_character). It only implicitly references chapter_text via 'chapter prose'. No additional meaning is added beyond the schema.

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 it generates draft entries from chapter prose, extracts structures, maps to canonical schema, and returns candidates sorted by adoption likelihood. It distinguishes from sibling tools like add_facts (commit) and retag_fact (refine).

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 tells to use after writing chapter text to avoid duplicate work, and guides to check high_new then use add_facts. It also suggests retag_fact for refinement if needed. Missing explicit when-not-to-use but alternatives are given.

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