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

Beyond the annotations (read-only, idempotent, non-destructive), the description discloses crucial behavioral traits: a result cap of 10 per request (lower than search_speeches), pagination semantics with 'next_start_record' (null indicates end of results), and the Japanese-first indexing behavior that affects matching. These are non-obvious and valuable for correct invocation, and they are not present in the 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 comprehensive yet tightly written. Every sentence adds distinct value: the definition, the requirement, the return fields, the language caveat, and the pagination note. It is front-loaded with the core purpose and requirement, and the caveats are logically placed. No redundancy or filler.

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?

With no output schema, the description fully specifies the return payload (issueID, house, meeting name, session number, issue number, date, permalink), covers the pagination mechanism, and explains the language behavior. It also addresses the requirement constraint. Given the tool's complexity (7 params, 0 required), this description is sufficient for an agent to invoke it correctly and interpret results.

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 100%, so parameters are already well-documented. The description adds the non-schema-visible constraint that at least one of query, meeting_name, or house is required, which is essential for validity. It also contextualizes the `query` parameter (matches speech text) and the `max_records` cap, though the schema already covers these; the added value is mainly the mutual-exclusivity requirement and the emphasis on the pagination offset.

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's function: searching Japanese National Diet meetings by name, chamber, or date range, and returns specific fields. It even clarifies the definition of a meeting (one committee or plenary session on one day), which is precise. It distinguishes itself from related tools by naming search_speeches and get_speech as downstream steps, implying this is the entry point for meeting discovery.

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 provides explicit conditions for invocation: 'Requires at least one of query, meeting_name, or house.' It also gives practical guidance on Japanese-first matching and warns that English keywords will under-match, which helps agents decide on appropriate query terms. Though it doesn't explicitly contrast with search_speeches, it implicitly guides the workflow by indicating how to use the returned issueID with that sibling.

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