web_info

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

With no annotations, the description carries the full burden, and it does disclose the no-argument behavior and the guaranteed top-level 'now' key in results. However, it does not explain the behavior of all topic values, notably 'execute_js', which may not be purely read-only, leaving some behavioral ambiguity.

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 brief, front-loaded with the core purpose, and every sentence adds useful information. It wastes no words and is easy to scan.

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?

The description is reasonably complete for a meta/introspection tool because it tells the agent to call with no arguments to pull the full contract, which effectively self-documents the rest. It still leaves topic-specific output and parameter expectations unspecified, but the contract mechanism compensates.

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 description coverage is 0%, so the description needed to compensate, but it only mentions the no-argument default behavior. It does not explain what values of 'topic' mean or how the free-form 'params' object should be structured for each topic.

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 clear verb ('Read') and a set of resources ('the contract, the page, the console, the network, or search/browser state'), which maps well to the tool's intent. It does not explicitly differentiate from the sibling 'web_action', but 'read' versus action is reasonably implied.

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?

It gives a concrete usage rule for the no-argument case: calling with no arguments returns the whole contract and removes the need for an external skill file. It does not explicitly say when to prefer this tool over 'web_action' or when a mutation-style action should be used instead.

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