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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds substantive context beyond them: a 14-day freshness window, max 10 / default 5 results, ranking by key-name and term overlap with newest-first tiebreak, and the outlet/time/link payload. It also discloses the feed's coverage limits (politics, economy, crypto, sports, entertainment) and that no article text is returned.

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 routing condition, then parameters, then return shape, then limitations — a sensible order with no filler sentences. The four quoted example queries are helpful for matching but make the opening more verbose than a shorter trigger summary would be.

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?

Given a read-only, open-world retrieval tool with three optional parameters and an output schema, the description covers trigger conditions, input forms, result count and ranking, freshness window, and the main failure mode (no results for niche markets). Nothing an agent needs to call it correctly or set expectations 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 coverage is already 100%, so this is a bonus: the description clarifies that market accepts a slug, a supported market or event link, and that plain words are treated as a topic, and that query combined with market narrows that market's news rather than searching globally. The default of 5 for limit is repeated from the schema rather than added to.

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 ('get news/headlines for a prediction market or topic') and enumerates the trigger phrasings an agent would hear. No sibling tool does news retrieval, so intent separation from search_markets, get_market_odds etc. is unambiguous.

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?

Opens with an explicit 'Use this when the user asks for news, headlines or recent developments' condition plus four realistic example utterances, and names search_markets as the source of slugs. It also states the when-not: it is not a full web search and may return nothing for niche markets.

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