Web search (Model Studio)

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

With no annotations, the description carries the full burden and does unusually well on the cost dimension: it names the billing model, a concrete price (~$10/1k searches in Singapore), and an explicit operational guardrail ("ask before bulk use"). It leaves gaps on authentication/plan requirements, rate limits, and failure behavior, which keeps it off a 5.

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 tight sentences: capability first, use cases second, cost caveat last. No filler, and the most decision-relevant fact (it returns a synthesized answer, not raw pages) is front-loaded.

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?

For a two-parameter read tool with full schema coverage and no output schema, the description covers purpose, return values, ideal use cases, and cost. An agent has everything needed to decide to call it and to warn the user about spend.

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 both parameters are already documented in the schema, and the description adds nothing about query phrasing or max_output_tokens beyond what is there. Baseline 3 is appropriate when the schema does the heavy lifting.

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 live web") plus the mechanism (Model Studio's built-in web_search tool) and the return shape ("a synthesized answer with source links"). It implicitly separates itself from extraction-style siblings by promising a synthesized answer rather than raw pages, but it never names an alternative, so differentiation is inferential rather than 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?

Gives concrete positive triggers — "news, prices, releases and anything after your training cutoff" — which is exactly the context an agent needs to decide whether to search at all. It omits when NOT to use it (e.g., when a URL is already known and web_extract would suffice) and never names an alternative, so it stops short of the 5 bar.

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