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

Annotations already cover safety (readOnly, idempotent, openWorld, non-destructive), and the description adds genuinely non-obvious behaviour: rate limits per IP with the exact error semantics, and the cross-portal duplication quirk (same tender appears once per portal with different uids; same title+authority+deadline means one tender). That dedup rule materially changes how an agent should interpret results.

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 routing are front-loaded in the first two sentences, and the coverage/limit/dedup details each carry operational weight. It is long, though: the 'Key filter parameters' enumeration duplicates the schema and the five example questions are repetitive, so a little trimming would help.

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 search tool with no output schema, the description compensates well by enumerating the returned fields and by explaining index coverage versus source coverage (190k+ notices vs 100k+ indexed), the update cadence, and deduplication. Nothing an agent needs to issue a correct call and interpret results is missing.

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 12 parameters (including enum values and repeat-for-OR semantics) are already documented. The description only re-lists 'key filter parameters' (Bundesland, status, cpv, nuts, deadline_after/before, notice_type), which is redundant rather than additive; baseline 3 is appropriate.

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 gives a specific verb (semantic search) and resource (German and EU public tenders), then lists exactly what is returned (ranked notices with AI summary, deadline, authority, CPV/NUTS, uid, notice_id). It explicitly names the sibling vergabe_liste as the tool for non-semantic, filter-only queries, so an agent can discriminate without opening a 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?

Routes the agent explicitly: topic/keyword/industry requests go here, 'structured filter queries without a topic description' go to vergabe_liste, and just-published notices newer than the index are found via vergabe_liste (order_by=publication_desc). It also documents the rate-limit escape hatch (vergabe_liste's q parameter) and states the ~10 queries/day/IP cap with 429/Retry-After behaviour.

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