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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. Beyond that the description adds genuine context: the data source (ParlGov), the historical depth (1949 onward), and the exact facts returned per election (confidence-vote day, duration, rotation, dissolution when no government formed). It doesn't cover response shape or size, but for a read-only reference tool this is solid added value.

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?

Scope is front-loaded ('Every Knesset election since 1949'), which is good, but the whole definition is one sprawling semicolon-chained sentence mixing election data, government composition, and pairwise party co-governance. Parsing it costs effort; splitting the pairwise-co-governance clause into its own sentence would help at no length cost.

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?

No output schema exists, so the description has to carry return-value semantics — and it does, enumerating the per-election fields and the pairwise co-governance dimension. The only gap is that it doesn't characterize the shape of the response (one record per election? one row per pair?) or its approximate size.

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?

There is a single parameter (lang) with 100% schema description coverage and an enum of four languages, so the schema fully documents it. The description never mentions the language parameter or what localization affects (names vs. narrative text). Baseline 3 is appropriate when the schema does all the work.

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 names the exact resource — every Knesset election since 1949, the first government after it, confidence votes, prime minister and rotation, parties holding ministries — so an agent knows precisely what corpus this returns. It doesn't name the sibling get_formation as the current-formation alternative, but the closing 'History, not a forecast' does scope it against a live/forecast tool. Clear and specific, just short of explicit sibling routing.

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?

Usage is implied rather than stated: 'History, not a forecast' tells the agent this is retrospective data, and the pairwise 2026-party co-governance element hints at a coalition-history use case. There is no explicit 'use this when…, use X instead' sentence and no mention of when the tool would be the wrong choice relative to get_formation or check_coalition.

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