Search Hansard Debates

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

Annotations already cover read-only, idempotent, non-destructive, open-world. The description adds genuinely useful context beyond that: which fields are returned (citation-grade metadata), the pagination model (limit+offset honour upstream), and that the source is authoritative and should not be supplemented by web search or training data. It does not disclose rate limits or failure modes, but the additions are substantive.

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?

Front-loaded and clearly sectioned (search, return fields, drill-down, exclusions, pagination, authority). Slightly dense and multi-topic for a single description, but every block earns its place. The drill-down sentence is somewhat redundant with the usage-guidelines section.

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 a 9-param, 3-enum, output-schema-bearing search tool, the description covers just about everything an agent needs: what it does, what it returns, how to drill below the preview, how to paginate, what NOT to do, and authoritative-source expectations. With an output schema present it correctly avoids over-explaining return values.

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 baseline is 3. The description still adds value with the non-obvious guidance that Hansard matches words spoken in speeches, not bill titles, and that member name text-search is silently ignored (the reason member_id exists). That is a semantic insight the schema alone doesn't convey, raising this above baseline.

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+resource+scope ('searching Hansard by topic, bill title, or text phrase') and explicitly contrasts itself with siblings: it says NOT to text-search by member name and routes to parliament_find_member / parliament_get_debate_contributions. It also distinguishes topic search from debate drill-down. This is precise enough for an agent to select it over law_parliament_member_debates and law_parliament_get_debate_contributions.

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?

Explicit when-to-use (topic/bill/phrase search) and when-not (member-name lookup), plus the canonical chained workflow (find_member → get_debate_contributions) for verbatim retrieval. It even names parliament_policy_position_summary for topic breadth. This is a complete routing guide.

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