web_search

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

Without annotations, the description should disclose behavior. It mentions it is 'source-only', routes across providers, and returns various metadata (routing receipts, provider attempts, cache provenance, typed errors). This provides some transparency but lacks details on rate limits, idempotency, or typical failure modes.

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 concise with two sentences, front-loading the main purpose. It is efficient, though some jargon ('v3 evidence') could be clarified.

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 complexity (14 parameters, no output schema), the description provides a brief overview but lacks details on return format, error handling, and the meaning of 'v3 evidence'. It is minimally adequate but could be more comprehensive.

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% and the description does not add semantic value beyond what the parameters' schemas already provide. The baseline of 3 is appropriate as the description does not enhance understanding of individual parameters.

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 identifies the tool as a web search that routes across multiple providers, distinguishing it from the sibling web_extract. However, it could be more explicit about returning search results and the meaning of 'additive v3 evidence'.

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?

Usage is implied from the name and description: use this for web search. However, there are no explicit guidelines about when to use this versus the sibling web_extract, nor are there any exclusions or prerequisites mentioned.

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