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

With readOnlyHint=true and openWorldHint=true, annotations already cover safety and scope. The description adds useful behavioral detail: results are ranked, include title/URL/date/extract, and come from Perplexity Search. It does not mention the quote=true branch, where a price is returned instead of results, but that is covered by the schema.

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 front-load the use case and then give the essential return information. Every clause 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?

For a simple read-only search tool, the description covers trigger, scope, and return shape even without an output schema. The quote behavior is only in the schema, but it is not hidden, and no pagination or rate-limit details are essential here.

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 schema already explains both query and quote. The description adds minor query context with example topics but does not elaborate on how to use the quote flag or how query syntax should be formed.

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 clear trigger: use when the answer is outside SWOGE data, and it specifies the output as ranked results with title, URL, date and extract. It separates web search from internal-data tools, though it does not explicitly differentiate from sibling tools like osint_lookup or ask_agent.

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?

"Use this when the answer is outside SWOGE data" is an explicit when-to-use condition and the examples (news, projects, teams, people) clarify scope. It does not name an alternative tool or an explicit when-not-to-use rule, so it stops short of full routing guidance.

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