get_state

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

Annotations already provide readOnlyHint=true. The description adds rich behavioral context: facts have chapter and narrated_in, the two slicing methods (as_of_chapter, as_of_narrated), and the concept of flashbacks. It also explains subject filtering. No contradiction with annotations.

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 paragraph that is front-loaded with the purpose, then explains temporal axes, filtering, and usage. Every sentence adds value; no waste.

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 no output schema and 4 parameters (none required), the description fully covers return values (facts with chapter and narrated_in), parameter semantics, and usage context. It is complete for the agent to use the tool correctly.

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%, so the description compensates by explaining 'subject' (フィルタリング), 'as_of_chapter', and 'as_of_narrated' with detailed temporal semantics. The branch parameter default is implied from schema but not restated. It adds significant meaning 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 the tool returns current valid facts in a branch, with temporal dimensions. It uses a specific verb ('返す', return) and resource ('facts'), and distinguishes from sibling tools like add_fact by being read-only and offering temporal slicing.

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 gives clear usage context: '章を書く前の状態確認に使う' (used to check state before writing a chapter). It explains the two temporal axes and filtering, but does not explicitly mention when not to use or provide alternatives to other tools.

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