Classify text into exactly one of your 2-20 labels (support triage, intent detection, content routing) — the answer is validated against your label list, so you always get a real label back. $0.005/call via x402.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Text to classify (truncated to 8,000 characters) | |
| labels | Yes | 2-20 candidate labels; the response is exactly one of them |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden. It adds valuable behavioral guarantees: 'the answer is validated against your label list' ensures a real label is returned, and the pricing ($0.005/call via x402) is an extra non-obvious detail. It does not cover failure modes, but the tool's simple classification behavior makes this less critical.
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 a single well-structured sentence that front-loads the action and packs in the label constraint, use cases, validation guarantee, and pricing. Every phrase earns its place with 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?
This is a simple two-parameter tool, and the description plus schema fully specify inputs, output behavior (exactly one label), validation, and cost. No output schema is needed because the labels parameter already states the return characteristic, and the description adds meaningful context for real-world use.
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 100%—both parameters are fully described in the schema (text truncation, label constraints, response guarantee). The description's mention of '2-20 labels' and the response being one of them largely repeats schema content, providing no new parameter-specific meaning beyond context.
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: 'Classify text into exactly one of your 2-20 labels.' It also names concrete applications (support triage, intent detection, content routing) that immediately distinguish it from sibling tools like sentiment or extract_keywords.
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 provides clear usage context by listing example applications, and the phrase 'your 2-20 labels' implies it is for custom labels. However, it does not explicitly mention when NOT to use it or name alternative tools, so it lacks explicit exclusions or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tool groups are nearly indistinguishable: wallet_analyze, wallet_spy, and base_wallet_profile all inspect wallets; batch_extract, batch_url_json, and x401_batch_extract all batch-extract URLs; route_task, agentcore_route, and mpp_route all perform routing. An agent would need to read very carefully to avoid selecting the wrong tool.
All names are snake_case, but there is no consistent verb_noun or namespace pattern: many are noun-only (inference, echo, sentiment, server_time), some are prefixed by domain (bazaar_, base_, x402_, rep_), and action prefixes vary widely (fetch_, compile_, extract_, purchase_, route_). The naming is readable but not predictable across the set.
Seventy tools is an extremely large surface for an agent to choose from, and most appear to be independent paid service wrappers. This exceeds the 50+ extreme mismatch threshold in the calibration and creates an overwhelming selection problem.
Relative to its apparent purpose—exposing x402 payments and Bazaar market data—the coverage is extensive: diagnostics, preflight, settlement verification, receipt lookup, wallet checks, Bazaar analytics, web extraction, and text processing are all represented. The main gaps are operational side-effects like creating or updating a Bazaar listing, but those appear to be outside this read/purchase surface.