web_search

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

Annotations already declare readOnlyHint=true, so the bar is lower. The description adds useful behavioral context beyond that: complementary queries may run in parallel, stopping after an authoritative source, and the tool returns the raw xAI Responses API body. This gives the agent a clear picture of execution behavior and output format without contradicting the read-only hint.

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?

The description is a single paragraph with five sentences, each serving a distinct purpose: usage trigger, parallel query allowance, stop condition, sibling differentiation, and follow-up. There is no fluff, and the most critical information is front-loaded. It is slightly dense but each 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?

Given the tool's simplicity (one parameter), no output schema, and read-only annotation, the description covers all essential aspects: when to use, alternatives, follow-up actions, operational heuristics, and the return format. An agent can confidently invoke it correctly without additional context.

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 parameter 'query' is already well-described as 'The question or search query to investigate'. The description does not add additional syntax, formatting, or examples beyond the schema. It mentions parallel queries, but that is not specific to the parameter's meaning. Given full schema coverage, the baseline of 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 clearly states the tool's purpose: discovering current information across the public web when no exact URL is known. It uses a specific verb ('discover') and resource ('public web'), and distinguishes itself from sibling tools (x_search for X-only content, web_fetch for page verification). This leaves no ambiguity about what web_search does.

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?

Explicitly states when to use the tool ('when no exact URL is known and current information must be discovered'), when not to (use x_search for X-only content), and the follow-up action (call web_fetch after finding a page to verify). It also provides operational guidance on parallel queries and stop conditions, making the decision tree fully transparent.

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