国会会議録の発言検索

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

No annotations are provided, so the description carries the behavioral burden. It discloses the output format (excerpts per speech plus links) and the cross-cutting constraint that at least one condition must be specified, which are meaningful behavioral facts. It does not explicitly state read-only nature or discuss pagination/rate limits, leaving minor gaps, but 'search' strongly implies a non-mutating read operation.

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?

Four well-structured sentences: purpose, when to use, return shape, and invocation constraint. No sentence is wasted, and the most important scoping and constraint details are front-loaded appropriately.

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?

For an 8-parameter search tool with no output schema, the description explains the return shape and the minimum-filter requirement, which are critical for correct use. The schema handles parameter details including pagination via start, though the description does not mention pagination explicitly; overall it is complete enough to call 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 100%, so the baseline is 3. The description adds a valuable cross-parameter constraint not enforced by the schema: at least one filter condition must be supplied. This helps an agent avoid a zero-parameter invocation that the schema would technically allow.

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?

States a specific verb and resource: searching speeches in Diet proceedings (both houses, plenary and committee). This is clearly distinct from the law-text-oriented sibling tools such as find_law or get_article. An agent can tell what this tool does without opening the schema.

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?

Gives clear context for use: checking legislative intent, government answers, and constitutional/provision interpretation in the Diet. It does not name alternatives or exclusions, but the domain is narrow enough that implicit contrast with law-text search is clear. The requirement to specify at least one filter is a useful usage constraint.

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