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

Annotations cover the safety profile (readOnlyHint=true, openWorldHint=true), so the description's burden is lighter. It nonetheless adds real information beyond the annotations: the exact shape of results per mode ('title, url, snippet, position' plus knowledge graph/featured snippet), and a credit-cost model with the notable caveat that credits are 'charged only when a call succeeds.' Pagination and error/rate-limit behavior are the only material gaps.

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 tightly packed sentences with zero filler, ordered purpose -> return shape -> routing -> cost. Every clause carries information an agent needs (mode outputs, sibling alternatives, per-call credits), so nothing is padding.

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, and the description compensates by describing returns per mode. With annotations covering read-only and open-world semantics, all five parameters documented in the schema, and costs stated, an agent has everything needed to select and invoke this tool 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 baseline is 3 and the schema already defines every parameter. The description goes slightly beyond it by tying each mode value to a concrete output form (serp = organic results, ai = written answer with cited URLs, deep = both), which is the one piece of mode semantics the enum text only partially conveys.

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 ('Search the web') and immediately enumerates the three distinct modes (SERP, AI synthesis, both), so the agent knows exactly what capability is on offer. It also names the two nearest siblings (scrape, research) and the boundary condition that separates them, which is the strongest form of differentiation.

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?

Gives explicit when-to-use ('current facts, news and finding pages') plus two named alternatives with their selecting conditions: 'To read one page in full use scrape; for a report built from many sources use research.' Nothing about routing is left to inference.

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