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

Annotations only declare readOnly/openWorld/idempotent; the description adds substantive behavior well beyond that: available=false vs available=true semantics for missing vs published-empty arrays, snapshot_changed handling, decision_not_found on absent decisions, and that IDs may remain unresolved. This is exactly the safety and state-contract context the annotations cannot 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?

There is almost no wasted clause, but the entire definition is one dense semicolon-chained run with no sentence or bullet structure, and it leads with the non-default sittings mode before revealing that decisions is the default. Content density is justified; readability is not.

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 13-parameter, four-mode tool this is unusually complete: input requirements per mode, paging/snapshot lifecycle, error outcomes (decision_not_found, snapshot_changed), and availability semantics are all covered, and an output schema exists so return shape need not be restated.

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 coverage is 100%, so the baseline is 3, but the description still adds meaning beyond the schema: mep_id returning independent recorded and intended positions 'without a roster lookup' and the caveat that empty positions do not prove absence from the vote, plus document_id descendant matching before paging. The resolve_names/roster_term relationship is reinforced rather than newly explained, keeping it from a 5.

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 resources precisely (sittings, decisions, voters) and specifies a verb per mode, and it is clearly the plenary-vote tool among siblings like euparl_get_mep and euparl_search_documents. It never explicitly states what it is not or names a sibling, and it opens with the least-common mode (sittings) in a way that can momentarily obscure that 'decisions' is the default.

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?

Explicit when-to-use per mode: 'Mode decision requires decision_id', 'Mode voters requires decision_id and one position', 'sittings with mode sittings and year'. It also states hard exclusions (rejects nondefault paging and snapshot for decision mode) and the resume strategy (page.next_offset with snapshot, restart at 0 after snapshot_changed).

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