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

With no annotations, the description itself must disclose behavior. It does state that the tool queries multiple live sources and returns evidence plus source URLs, which is useful. It omits details like result counts, rate limits, or treatment of conflicting claims, but the core behavior is disclosed.

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?

A single front-loaded sentence carries the entire meaning with no filler or redundant restatement of the tool name. It is appropriately sized for a one-parameter tool.

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 one-parameter tool the core behavior and return type are stated, which is barely adequate. However, without an output schema or annotations and with several similar sibling tools, the description leaves gaps around query format and evidence structure that an agent needs to invoke it confidently.

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 0%, so the description needs to clarify the query parameter, but it only implies that 'query' is the search string. No guidance is provided on formatting, supported operators, or whether URLs or domains are acceptable inputs.

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 names a specific operation ('Search multiple live web sources') and a distinctive output ('structured factual claims with supporting evidence and source URLs'). This distinguishes search_evidence from sibling search tools like search_read and search_extract, which are not described as returning evidence-backed claims.

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?

No guidance is given for when to choose this tool over search_read, search_extract, research_answer, or web_intelligence. The description only states what it does; there is no when-to-use, when-not-to-use, or alternative-routing context.

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