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

Annotations already declare readOnly/idempotent/openWorld, so the safety profile is covered; the description adds genuine behavior beyond them. It discloses result ordering ('newest first'), the default session fallback, and the pagination contract (follow nextOffset with identical filters) — the latter not derivable from the input schema since nextOffset is returned, not passed. Minor gap: it doesn't mention paging can end early before limit.

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 tight sentences with the core action and filter list front-loaded, followed by the result-ordering and pagination protocol. No filler. The second sentence compresses two distinct instructions ('newest first' and 'pass to canparl_get_vote'), which slightly blurs structure but costs little.

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 nine-parameter, all-optional search tool with a live output schema, the description covers the essentials: what is searched, default ordering, session defaulting, and how to page and hand off to canparl_get_vote. With rich annotations and full schema coverage, the remaining omissions (page-size clamping behavior) are already documented in the limit parameter.

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 all nine parameters are already self-documenting (limit caps, date formats, billCode aliases, result aliases). The description adds only the omitted-session resolution rule, which the schema also states, plus the 'identical filters' constraint for offset continuation. Baseline 3 is appropriate given the schema carries the parameter burden.

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 ('Find recorded House divisions') plus the exact filter dimensions (bill, result, document type, date, subject) and a scope limit ('in one session'). It also clarifies the boundary against canparl_get_vote by naming the handoff, so an agent can distinguish this search tool from its detail-fetch sibling.

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 operational guidance: search here, then pass 'session plus number to canparl_get_vote', and follow nextOffset with identical filters. It explains session omission ('resolves from the current official bill feed'), which is a real decision point. It stops short of explicit exclusions (e.g. use canparl_search_bills for bill text), so not a 5.

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