Run native X search queries in a signed-in browser to retrieve posts or people records, then save a local snapshot of the bounded results for later reference.
Search X through the browser with native X search operators. Returns a bounded sample and saves a local snapshot. People returns user records; other tabs return posts.
| Name | Required | Description | Default |
|---|---|---|---|
| tab | No | latest | |
| limit | No | ||
| query | Yes | ||
| maxScrolls | No |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only, idempotent, open-world behavior, and the description adds meaningful non-obvious traits: the result is bounded, a local snapshot is saved, and tab selection changes the record type returned. This goes beyond the structured metadata without contradicting it.
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?
Three compact sentences each carry distinct information: purpose, output/side-effect behavior, and tab-specific semantics. No filler or repetition; key facts are front-loaded.
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 four parameters and no output schema, the description gives a good overview but leaves gaps: limit and maxScrolls semantics, what 'bounded sample' means in practice, and how the snapshot relates to snapshot sibling tools. It is adequate for basic selection but not fully self-contained.
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 must compensate. It does clarify the tab parameter's effect on return type and hints at query syntax, but limit and maxScrolls are only indirectly covered by 'bounded sample' and receive no concrete semantic explanation.
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 uses a specific verb-resource pair ('Search X through the browser') and adds concrete behavioral details: native operators, bounded sample, local snapshot, and tab-dependent result types. This clearly distinguishes the tool's purpose from snapshot-read and thread/profile sibling tools.
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?
The description implies usage for live X searches and explains how tab choices change results, but it does not explicitly state when to prefer x_search over siblings like x_saved_search_run or x_trends, nor does it mention exclusions. Usage context is present but not contrastive.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.