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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds behavioral specifics: it returns only the top 3 titles with links, and that advanced features are gated behind a subscription. This goes beyond the structured annotations and provides useful context for the agent.

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?

The description is two sentences. The first clearly articulates the tool's core function and output; the second states the limitation and upgrade path. Every phrase contributes meaning, with no redundant or filler content.

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 the simple input (one string), the presence of an output schema, and the read-only annotation, the description is largely complete. It explains the scope ('recent AI news'), result count (top 3), and the subscription boundary. Minor ambiguities like the exact meaning of 'recent' are not critical.

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?

The input schema has 100% coverage for the single 'query' parameter, describing it as 'Search terms.' The description does not add additional detail about parameter semantics, such as syntax, length restrictions, or examples. With full schema coverage, the baseline of 3 is appropriate.

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?

Description states the tool performs a 'quick teaser search over recent AI news' and specifies the output: 'top 3 matching titles with links.' This is a clear verb+resource pair and distinguishes it from the sibling get_* tools, which are not search tools. The teaser scope is explicit.

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?

The description clearly indicates when to use this tool ('Quick teaser search') and contrasts it with the full-text search capability that 'requires a Horizon subscription.' This implies that for full-text, filters, or history, users should not rely on this tool. However, it does not explicitly name an alternative tool, though none of the siblings fill that role.

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