Search arXiv preprints in CS, physics, math, biology. Titles, authors, abstracts, categories.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results, default 20 | |
| query | Yes | Search terms | |
| category | No | e.g. cs.CL, cs.LG |
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?
With no annotations, the description carries full burden. It fails to disclose behavioral traits such as pagination, sorting, rate limits, or result format. Only the fields searched are mentioned.
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 short sentence, which is concise but lacks important details like result structure or usage instructions. It is not densely informative.
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 no output schema and simple parameters, the description should explain return values or expected result format. It does not, leaving agents uninformed about tool output.
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 baseline is 3. The description adds marginal value by confirming fields searched, but the schema already documents each parameter adequately.
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 clearly states the tool searches arXiv preprints across specific domains (CS, physics, math, biology) and the fields searched (titles, authors, abstracts, categories). However, it does not explicitly differentiate from sibling tools like search_papers or search_openalex.
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 is provided on when to use this tool versus alternatives. The description implies usage via domain scope but lacks explicit context or exclusions.
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.
Tools cover very diverse domains (weather, FDA, legal, crypto, etc.), so cross-domain confusion is low. However, within domains there is notable overlap: multiple food recall tools (food_recall_check, food_safety), multiple weather tools (weather_current_global, weather_forecast_grid, weather_alerts, weather_bias), and several Polymarket-related tools. This can cause agent misselection.
Naming is inconsistent: some tools use verb_noun (search_arxiv, scrape, validate_agent_manifest), others use noun phrases (smart_money, space_weather, tide_data), and some are long descriptive phrases (cross_platform_arb_scan, polymarket_event_scan). No single pattern is followed, making predictions difficult.
95 tools is excessively high for any coherent purpose. The server appears to be a random aggregation of APIs with no clear scope. Such a large catalog overwhelms agents and dilutes utility; most tools could be split into specialized servers.
Although many domains are touched, each is covered only shallowly. For example, weather lacks historical data, legal lacks case details beyond court opinions, and financial lacks stock prices. There are obvious gaps like no user authentication or data persistence. The tool set feels like a collection of endpoints rather than a cohesive service.