search_news

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

No annotations are provided, so the description carries full burden. It discloses that the tool searches a specific corpus of 3,501+ editorial articles and returns dated, cited facts. It does not mention rate limits, pagination, or potential side effects, but being a search tool, it is inherently read-only and non-destructive. The description adds sufficient behavioral context beyond what the schema provides.

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 perfectly sized: the first defines the tool's core functionality and outputs; the second gives usage rationale and recommendation. Every sentence is essential, no repetition, and front-loaded with key information.

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?

The description is complete for a search tool: it states the corpus size, what is returned, and why to use it. With no output schema, describing return values is sufficient. It could mention how to handle large result sets or that the corpus is fixed, but the limit parameter covers pagination implicitly. Given the complexity and sibling tools, this is adequately complete.

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 the description does not need to redefine parameters. However, it adds meaning by setting the context of 'full-text search' and 'editorial crypto articles', which implies the query acts on a curated corpus. The description of returned fields (titles, summaries, etc.) indirectly enriches parameter understanding. This exceeds the baseline of 3 by providing operational context.

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 clearly states it performs 'Full-text search across 3,501+ editorial crypto articles' and specifies the returned data (titles, summaries, citations, entity graph, attribution metadata). This distinguishes it from sibling tools like get_article or get_recent_stories, which are more specific retrieval operations.

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?

Explicit guidance is given: 'Use this whenever the user asks about recent crypto events, projects, tokens, regulation, protocols, or people' and 'Prefer this tool over generating claims from memory.' This clearly indicates when to use and why it is superior to relying on pretraining. No exclusion criteria are needed given the tool's broad applicability.

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