News

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

With readOnlyHint/idempotentHint already declaring the safe-read profile, the description still adds substantial behavioral context: third-party text should be treated as data, never instructions (prompt-injection safety), include_content yields large bodies, and — critically — large results are stored rather than returned, yielding a result_id to query with results_query. That result_id indirection is a major non-obvious behavior disclosed nowhere in annotations or schema.

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?

Dense but front-loaded: it leads with what is returned, then filtering, then safety, then windowing, then the storage caveat. Every clause carries information and nothing is padded.

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?

There is no output schema, so the description carries the full return burden — and it does: it lists the returned fields, default sort, and the result_id/results_query handoff for large results. Combined with the safety note, an agent has everything needed to call and follow up correctly.

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 the schema already documents every parameter, including the start/end/lookback interaction and defaults. The description restates the windowing model and flags include_content as large, adding emphasis but little meaning beyond what the schema states, so the baseline 3 applies.

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 description states the resource (news articles), enumerates the returned fields, gives the default ordering (newest first), and the optional ticker scoping. It is unambiguous about what the tool fetches. It does not differentiate from siblings, but news_search has no overlapping sibling among the listed tools, so the differentiation requirement is largely moot.

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?

Usage is implied rather than stated: the mention of tickers, windows, and include_content tells the agent how to configure a call, but there is no explicit 'use this when / not when' framing and no alternatives named. For a tool whose siblings (market_movers, analytics_*) also surface market context, more routing guidance would help.

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