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

Annotations already declare openWorldHint=true and destructiveHint=false, so the description doesn't need to restate those. It adds valuable behavioral context: returns up to 10 results, settles $0.005 USDC, and no charge on failure. This goes beyond the annotations by disclosing cost and failure behavior.

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?

Three sentences with zero waste. The core purpose is front-loaded, usage guidance follows, and cost/failure behavior is stated compactly. Every sentence earns its place.

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 covers purpose, usage boundaries, result count, and cost behavior. With an output schema present, return values don't need to be explained. Minor gap: doesn't mention pagination or how to handle ambiguous queries, but for a search tool with this schema and annotations, it's nearly 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 description coverage is 100%, so the schema already documents both parameters (query and limit). The description adds the 'up to 10 results' constraint, which aligns with the limit maximum, but doesn't add much beyond the schema. Baseline 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?

The description states a specific verb ('Web search'), a clear resource ('ranked results with title, URL, description, and source domain'), and explicitly frames it for agent consumption. It distinguishes itself from sibling tools like compute_infer or get_market_signal by focusing on current web information retrieval.

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 explicitly states when to use it ('MUST be invoked when an agent needs current web information') and when not to use it ('Do NOT use for cached/static data lookups'). This gives clear routing guidance relative to alternatives.

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