searchReal-time web search - up to 10 results with title, URL, a cleaned page extract and publish date when available, plus an optional short summary. Also accepts up to 5 queries in one call, merged and de-duplicated - one call instead of five. No account, no API key, no quota. Try a real, live sample at GET /search/sample.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| extract | No | ||
| summarize | No | ||
| max_results | No |
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 discloses real-time behavior, a 10-result cap, cleaned page extracts, publish date availability, optional summaries, multi-query merging/deduplication, and the free-first-call pricing model. Minor gaps remain around max_results semantics and error behavior, but the main behavioral traits are well covered.
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 front-loaded with purpose and result details, then covers batching, pricing, and a sample endpoint. All sentences carry useful information, though the sample URL and pricing details add slight extra length; still far from verbose.
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 no annotations, the description does a good job covering return fields, multi-query behavior, and access requirements. It could be more complete by explicitly stating how max_results maps to the result count and what 'normal price' entails, but the essential information for a correct call is present.
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%, but the description adds meaning beyond parameter names: 'up to 5 queries in one call' explains query arrays, 'cleaned page extract' clarifies extract, and 'optional short summary' clarifies summarize. The max_results parameter is not explicitly tied to the 'up to 10 results' cap, so it is not fully compensated.
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 'Real-time web search' and specifies result contents ('title, URL, a cleaned page extract and publish date when available, plus an optional short summary'), giving a clear verb+resource scope. The sibling tools are jobs and translate, so there is no ambiguity about what this tool does.
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 context about when to use the tool: web search with real-time results, no account/API key/quota, and a one-call batch option. However, it does not explicitly address when-not-to-use or directly compare against sibling tools, so it stops short of full exclusionary guidance.
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.
Search and translate are clearly distinct, and jobs is differentiated by its multi-query synthesis into a JSON brief, though the name 'jobs' is vague and could initially be confused with search or background task management. The detailed descriptions resolve most ambiguity.
All tool names are lowercase single words, which is simple, but search and translate read as verbs while jobs reads as a noun. There is no verb_noun or consistent action-oriented pattern, though the naming is still readable.
Three tools is well-scoped for a research/translation utility server. Each tool covers a substantial capability and justifies its existence without redundancy.
The core workflows of web search, multi-query research, and bulk translation are covered, with job polling and result retrieval mentioned. Minor gaps exist around explicit job lifecycle management such as cancelling or listing past jobs, but agents can likely work around these.