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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds behavior the annotations don't: it accepts either an id or a name, describes what 'topic' matches against (label, agenda item topic, dossier title), and explains the paging model for the whole term.

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?

It is front-loaded: the 'use this when' trigger comes first, followed by parameter hints in a logical order. A couple of sentences restate what the schema already spells out (from/to date filtering), which is minor redundancy but keeps it just below the top mark.

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?

There is no output schema, so the description carries the burden of saying what comes back, and it does so by enumerating the record's contents (group, committees, cohesion, defections, recent votes). Pagination limits are covered by the schema. It does not describe result shape or error cases, which is why it lands at 4.

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 real meaning: it clarifies topic is a substring match across three fields with concrete examples ('digital euro', 'Mercosur'), and ties from/to and page together into a 'read one period vs page through the term' strategy, which is cross-parameter guidance the schema does not provide.

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?

Opens with a specific trigger ('when the user asks about one Member of the European Parliament') and enumerates the returned content: country, political group, committees, group-cohesion rate, defections and recent roll-call votes. The resource is unambiguously a single MEP, which cleanly separates it from get_vote, list_votes, get_dossier and compare_groups.

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 lead sentence gives a clear use context ('the user asks about one MEP'), and the following sentences give practical routing for narrowing by topic, by date range, or by paging through the term. It stops short of naming an explicit alternative or a when-not condition, so a 4 rather than a 5.

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