reconcile_facts

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

Annotations declare readOnlyHint=true, and the description confirms it performs only matching and analysis without modifications. It additionally discloses filtering by known entities and zero anaphora resolution, and explains that output categories indicate potential fabrications or omissions. No contradictions.

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 paragraph that front-loads the core action and output. It efficiently covers key points without redundancy, though the Japanese text is dense and might benefit from clearer structuring for non-native readers.

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?

The tool is complex with 4 parameters and no output schema. The description explains the return value categories and matching logic, but does not detail all parameters or provide examples. This is adequate but not complete for full agent understanding.

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%; the description only explains the format of 'llm_facts' as an array of subject-predicate objects. Other parameters (chapter, chapter_text, pov_character) are not described, leaving their semantics unclear. With low coverage, the description should provide more parameter details.

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 identifies the tool's action: reconciling LLM-extracted facts with mechanism-extracted predicate-argument records on subject-predicate axes. It specifies inputs and output categories, distinguishing it from sibling tools like add_fact or delete_fact.

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 for identifying discrepancies between two fact sources but lacks explicit guidance on when to use this tool versus alternatives, and does not mention when not to use it. The note that differences are not definitive provides some context.

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