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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely non-derivable behavior: per-query cost ($0.01), variability in source coverage, and multilingual filing, which together warn that results may be incomplete or in a non-English language and that calls are metered. Missing only pagination/total-count behavior and whether results are deduplicated.

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?

Two sentences, front-loaded with what the tool is and what it returns, then a compact caveat block covering audience, coverage, language and cost. Nothing is redundant with the title, and the closing price note is one short clause rather than a paragraph.

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?

With no output schema, the description correctly compensates by enumerating returned fields, and it discloses cost and coverage caveats for a live external database. The remaining gap is scale behavior: with limit capped at 20 there is no statement about whether more results exist or how to page, which matters for an open-world search.

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 67%: `q` and `country` carry their own descriptions and examples, while `limit` is self-documenting via default 10 and bounds 1-20. The description adds no parameter-level meaning at all — it never mentions country filtering, the 20-result cap, or whether `q` supports operators versus plain full text. That matches the baseline 3 where the schema does the heavy lifting.

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?

"Search current notices in TED, the EU official procurement database" gives a specific verb (search) plus resource (TED notices), and immediately enumerates what comes back (buyer, title, description, CPV codes, publication date, deadline, source link). No sibling tool in this list touches procurement, so there is no ambiguity to resolve, but the scope is still stated precisely enough that an agent knows exactly what corpus is being queried.

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 phrase "Useful for sales-lead and market-intelligence agents" implies the use case, and the note that "source coverage and filing language vary" hints at limits on recall. However, there is no explicit when-to-use vs when-not, no mention of an alternative tool for non-EU procurement, and no guidance on when results would be sparse or when to re-query. Usage is inferable but not directed.

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