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

Annotations already declare read-only, idempotent, open-world, non-destructive behavior, so the lower bar applies. The description adds substantive context beyond them: which funder registries are actually indexed and what entity fields come back (title, funder, budget, coordinator, partners, dates). It does not discuss result limits or coverage gaps per funder, which keeps it below a 5.

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?

Front-loaded with the concrete questions the tool answers, followed by scope and return fields — the ordering is effective. The three quoted query phrasings are slightly repetitive, but each maps to a different funder/registry case, so the repetition largely earns its place.

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?

An output schema and full parameter descriptions already exist, and annotations cover the safety profile, so the description's job is to add source coverage and use-case framing — which it does. Minor remaining gap: no indication of how EC/CORDIS results differ in completeness from NSF/NIH coverage.

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 every parameter is already documented, establishing the baseline of 3. The description contributes only indirectly by naming the funder bodies (NSF, NIH, Wellcome Trust, CORDIS), which hints at valid values for the enum-less 'funder' parameter but gives no format rules or exhaustive list.

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?

States a specific verb and resource — 'search funded research projects' — and lists the funding sources covered (CORDIS for EC, NSF, NIH, Wellcome Trust). The quoted user-query phrasings ('Horizon Europe projects on X', 'CORDIS lookup for Y') make it immediately distinguishable from openaire_search_datasets and openaire_search_publications.

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?

Explicitly names the intended contexts: 'funding-landscape analysis, grant precedent research'. It gives clear when-to-use framing but no exclusions and does not name a sibling alternative for the adjacent publication/dataset lookups.

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