Cross-source search over 29 international news/AI/finance/tech sources (BBC,NYT,HackerNews,ArXiv,CNBC,FT). English keyword. Returns articles + source reliability(reputation). 100 free queries/day; key from POST /pipeline/v3/register.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | max results, default 10 | |
| keyword | Yes | English search keyword, e.g. OpenAI, Fed rate, quantum |
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 provided, so the description carries the full behavioral burden. It transparently discloses auth needs (key from POST /pipeline/v3/register), rate limits (100 free queries/day), and result content (articles + source reliability). The search wording also implies a read-only operation.
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 dense sentences front-load the core operation and then add source scope, return content, quota, and auth acquisition without filler. Every sentence earns its place.
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 only 2 simple parameters and no output schema, the description sufficiently covers source scope, input language, expected result, quota, and key acquisition. An agent can select and invoke the tool accurately without external documentation.
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%, with keyword format/examples and limit range/default already documented. The description adds little beyond repeating 'English keyword', so the 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 verb ('search'), a bounded resource (29 international news/AI/finance/tech sources), and a clear output (articles + source reliability). This differentiates it from sibling tools like qy_fetch_articles and qy_list_sources.
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?
Provides clear usage context: cross-source search, English keyword required, named source domains, and a daily query budget. It does not explicitly name alternatives or exclusions, but the search-vs-fetch-vs-list distinction is reasonably clear from scope and sibling names.
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.
Each tool targets a distinct resource (brief, articles, sources, notes read/write, news search). Minor overlap exists between qy_fetch_articles and qy_search_news (both return articles) and qy_daily_brief summarizes similar content, but categories vs keyword search vs daily digest provide enough separation.
All tools share the qy_ prefix with a verb_noun pattern (fetch_articles, list_sources, post_note, search_news, search_notes). qy_daily_brief is the only deviation (adjective_noun, no verb), but it remains readable within the set.
At 6 tools, the server is well-scoped for its purpose: content retrieval, source discovery, and an agent notes wall. Each tool earns its place without redundancy or bloat.
Core read workflows are covered (daily brief, article fetch, news search, source listing) plus a complete write/read pair for the notes wall (post_note + search_notes). Minor gaps exist, such as filtering the daily brief by category or fetching a specific article's detail, but agents can work around these.