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 and the description is not required to restate it. Beyond that it usefully discloses corpus scope (~22,400 EP procedures since 1999, ~90% with dated timelines), an explicit content boundary (Parliament steps only, NOT Council-internal deliberations), single-hit enrichment behavior, and the citation obligation. However, it never addresses limits on result size beyond the schema, pagination, or what a multi-hit response looks like versus a single-hit one, so it adds good context without fully describing response behavior.

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?

Despite its length, it is front-loaded: purpose and payload first, then the alternative-tool routing, then search modes, then coverage/source caveats. Most sentences carry distinct information (the Council-exclusion caveat, the citation rule, the coverage statistic), but the trailing boilerplate tag about non-AI original-data delivery does not help an agent select or invoke the tool.

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 zero-required-parameter lookup over a large external dataset with no output schema, the description supplies everything an agent needs: what a hit contains, when enrichment appears, the temporal coverage and its known gap, the source and its blind spot (no Council deliberations), and the mandatory citation format. Nothing material is left to inference.

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 the baseline is 3; the description earns an extra point by showing filters in combination (type='COD', committee='ENVI', only_trilogue=true) and by tying only_trilogue to a precise meaning ('dokumentierte Trilog-Einigung im Ausschuss'). It does not add syntax or format detail beyond what the schema already documents for reference, topic, or limit.

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 opening sentence names a specific verb and resource (tracking EU legislative procedures) and enumerates exactly what is returned: status, dated timeline, lead/opinion committees, rapporteurs and shadow rapporteurs, trilogue agreement, OJ publication, next scheduled date. It explicitly distinguishes itself from get_legislative_footprint (lobby side) and positions itself as the EU counterpart of search_drucksachen, so an agent can separate it from siblings without opening any 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?

It gives three concrete access paths (Aktenzeichen, topic, filtered by type/committee/only_trilogue) with literal example values, states that the lobby context only appears in a narrow exception, and routes the agent to get_legislative_footprint for rapporteur meetings on a dossier. The when-to-use-this-instead-of-that decision is stated outright rather than implied.

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