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

Annotations already declare readOnly, idempotent, non-destructive, open-world, and the description usefully adds that results are transparent rule-based scores rather than eligibility determinations, plus the 25-notice scan ceiling. "Free, read-only" merely restates the annotations, but the score-framing caveat and sampling limit are genuine additions beyond structured data.

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?

Four short sentences, each carrying a distinct fact (capability, return semantics, sampling limitation, cost/safety) with the core purpose front-loaded. Nothing is padded or repeated.

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 7-parameter, no-output-schema tool, the description covers what matters most: ranking semantics, the sample ceiling, and the fact that scores are not legal eligibility judgments. Remaining gaps are minor — the days/scope knobs and the requirement to supply keywords or CPV live only in the schema.

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 71%, so cpv, keywords, country, scan_limit, and max_results are already documented in the schema. The description adds "up to 25" which corroborates scan_limit's maximum, but calling CPV and keywords "optional" slightly understates the anyOf constraint that at least one is required, and days/scope get no treatment at all here.

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?

"Rank up to 25 recent TED notices using optional CPV and business keywords" gives a specific verb (rank), resource (TED notices), and scale bound, which separates it from the sibling search_tenders by implying ranked relevance rather than retrieval. It stops short of naming search_tenders explicitly, so the differentiation is inferred rather than stated.

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?

"Searches only a recent sample, not all TED notices" is a real scope caveat that tells the agent when this tool under-delivers, and "not eligibility decisions" sets a boundary on interpretation. However, it never names search_tenders as the alternative for full-coverage queries, so the agent must infer the routing itself.

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