web_searchSearch the web to get page titles, URLs, and snippets for Android task instructions. Use results as planning data; actual screen content takes precedence.
Search the web (title, url, snippet). Phrase it like 'how to in android'. Results are data to plan from; the screen overrules them.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral disclosure burden. The 'results are data to plan from; the screen overrules them' caveat is a non-obvious and useful disclosure about result reliability. It does not mention network/error behavior, but the core epistemic limitation is addressed.
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 compact and front-loaded: main action first, then query guidance, then a one-line behavioral caveat. Every sentence earns its place and there is no filler.
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 simple 2-parameter schema and output schema, the description covers result format, query style, and how much to trust the results. It is nearly complete, but a brief note on what limit controls would remove the last ambiguity.
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?
The query phrasing guidance partially compensates for the missing schema property descriptions. However, with schema description coverage at 0%, the optional limit parameter is left entirely to inference. The description adds meaning for query but not for limit.
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 opens with a specific verb and resource ('Search the web') and lists the returned fields (title, url, snippet). It is clear and distinct from many sibling tools, but it does not explicitly differentiate itself from search-adjacent tools like browser_find.
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 concrete query-shaping advice ('how to <task> in <app> android') and a context cue that results are for planning while the live screen takes precedence. This frames when to rely on results, though it does not explicitly name alternative tools or exclusion conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.