get_bill_history

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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses LIS data quirks (passage dates null in detail, committee recorded only here), defines field semantics (is_passage meaning, status after each event), and explains the vote_id → get_roll_call linkage. This exceeds what annotations would typically convey.

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 purpose is front-loaded in one clear sentence, and the second paragraph organizes field explanations densely — every sentence carries unique value (quirks, semantics, routing). It is slightly long for a 2-parameter read tool, but the density justifies most of the length.

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 the output schema exists, the tool's read-only nature, and 21 siblings, the description covers the core behavior, data quirks, response field semantics, and one cross-tool route. The notable gap is parameter documentation (0% schema coverage, no compensation in prose), though the parameter names are reasonably self-evident.

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% and the description never mentions bill_number or session_code, so it does nothing to compensate for the uncovered schema. The parameter names are somewhat self-evident, but the rubric requires the description to fill low-coverage gaps, and none of the requested-parameter semantics are addressed.

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 first sentence states a specific verb and resource — 'Chronological action history for a bill' — and the scope ('from prefiling to governor action') is explicit. This is clearly distinguishable from sibling tools like get_bill, get_bill_votes, get_bill_summaries, and get_bill_text.

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 implicit routing context: 'Passage dates live here' with the note that bill-detail passage fields are 'always null in LIS,' and 'this is the only place LIS records which committee holds a bill.' It also explicitly routes vote_id to get_roll_call. However, it never names an alternative for plain bill detail or states when not to use this tool.

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