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

Annotations already establish this as a safe, read-only, idempotent, closed-world operation, yet the description still adds substantive behavior: the data basis (HowTheyVote.eu bulk, ODbL licence), the methodological rule that DID_NOT_VOTE does not count as deviation, and the exclusion of non-attached members. What is missing is any statement about the shape of the result (a ranking, a per-group table, how many groups are returned).

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?

Purpose and the guiding question come first, followed by method and scope caveats, so it is front-loaded and reads as a coherent block. It is dense but each clause carries information; the trailing licensing/no-AI note is the only part bordering on boilerplate.

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 three-parameter, zero-required, read-only analysis tool with no output schema, the description covers the data source, the counting rule for absences, and the excluded population — enough for an agent to call it correctly and interpret results. The only real gap is that the return structure (ranking vs. table, per-term aggregation) is not described at all.

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 three parameters (term, date_from, main_only) are already fully documented including defaults and rationale. The description only restates that amendments are included by default ('inkl. Änderungsanträge') without adding format or edge-case semantics beyond the schema, so the baseline 3 applies.

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?

Names a specific verb and resource — comparing the voting cohesion (Fraktionsdisziplin) of EU parliamentary groups — and immediately frames the output question ('welche Fraktion stimmt am geschlossensten ab, welche bröckelt?'). It also anchors itself against a named sibling by declaring itself the EU counterpart of compare_parties (DE), so an agent can place it without opening the schema.

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 context for when the tool applies (EU level, named-vote cohesion) and explicitly bounds the population by excluding non-attached members with a reason. It does not spell out when to prefer other EU tools such as get_eu_scorecard or get_eu_positionsmatrix, so an explicit exclusion statement is missing, but the routing signal via compare_parties is strong.

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