web_search

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

No annotations are provided, so the description carries the full behavioral burden. It says 'Returns a snapshot of results', which is a useful hint, but there is no disclosure of whether the tab is navigated or replaced, whether the result is an accessibility snapshot vs. HTML, whether profile/cookie state is required, or anything about errors and rate limits.

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 engine enumeration duplicates the schema enum, and the final clause about 'ordinary browser navigation/network policy' is vague filler that distracts from the search semantics. Front-loaded purpose is good, but there is avoidable redundancy and an unclear sentence.

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 tool with no output schema and no annotations, the definition should explain the tab lifecycle and result shape. It gives a one-line return hint but omits how tabId behaves and what 'snapshot' implies, leaving real gaps for an agent to discover by trial.

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 documents query, tabId and engine with enum descriptions. The description mostly repeats the enum list and adds only one genuinely new detail: engine=custom relies on CAMOFOX_SEARCH_URL_TEMPLATE. Baseline 3 fits.

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?

States a specific verb and resource (search) and enumerates the 14 supported engine macros, so an agent knows exactly what it covers. The trailing phrase 'ordinary browser navigation/network policy' blurs the scope somewhat, but the core purpose is unmistakable.

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?

There is no guidance on when to use this versus the many siblings that also produce page content (navigate, navigate_and_snapshot, snapshot, get_links). It does not say whether a tab must already exist, whether it navigates the given tab, or when to prefer engine-specific macros over plain navigation.

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