Cleans raw social/X streams by stripping crypto shills and bot spam to isolate vendor complaint and buying intent signals.
De-noises raw social/X streams: Strips crypto shills and bot spam, isolating high-purity vendor complaint and buying intent signals.
| Name | Required | Description | Default |
|---|---|---|---|
| rawPosts | Yes | Array of raw social media or forum post strings |
Changes observed during successful MCP inspections.
v0.1.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full burden, yet it never states the return shape (filtered array? scored items? counts?), whether filtering is deterministic or model-based, or whether the call consumes credits despite a sibling named buy_cleansignal_credits. It does disclose the filtering criteria (crypto shills, bot spam), which is real behavioral content, but the operational gaps dominate.
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?
A single front-loaded sentence with the action leading and the target signals trailing. It is efficient, though 'de-noises' and 'high-purity' are marketing-flavored rather than operational wording.
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?
With no output schema and no annotations, the description is the only source of truth about what comes back, and it never says. For a transformation tool whose entire value is the output, missing return-value description and credit/cost implications leave a material hole.
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?
Only one parameter and schema description coverage is 100%, so the schema already documents rawPosts as an array of post strings. The description's mention of 'raw social/X streams' reinforces the input domain but adds no format, size, or batching detail beyond the schema; baseline 3 applies.
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 operation (de-noising / stripping spam / isolating complaint and buying-intent signals) on a specific resource (raw social/X streams). An agent can tell roughly what it produces, though the name-plus-description pair is somewhat jargon-heavy and does not distinguish it from the sibling scan_b2b_buying_intent, which appears to target the same signal class.
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?
No guidance on when to use this versus scan_b2b_buying_intent, no stated prerequisites on input (e.g. minimum posts, language, date window), and no exclusions. The agent must guess at the boundary between filtering and scanning.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.