Search Roundup's Japanese SME web marketing insights; return source excerpts and article links.
Scored across 1 tool
There is only one tool, so there is no possibility of confusing it with another. Its purpose (finding Roundup knowledge-base evidence) is clearly stated and bounded.
A single tool follows a clean snake_case verb_noun pattern. With no other names to compare against, there is no inconsistency.
One tool is thin even for a knowledge server; search alone leaves no complementary operations. It is defensible for a narrowly scoped retrieval source but sits at the borderline of 'too few'.
The search surface is described but there is no way to retrieve a full source, list available sources, or narrow by type. Notable retrieval-lifecycle gaps remain beyond returning 'source candidates'.
Find Roundup Q&A, Podcast and feature-article evidence for SME Web strategy, measurement, content, customer understanding and operating decisions. Not for live weather, general advice, private data, account credentials or Roundup service prices. Returns source candidates, not a final answer. Clarify ambiguous requests.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| max_results | No | ||
| include_historical | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description still adds real value by setting the output expectation ('Returns source candidates, not a final answer'), which prevents the agent from treating results as a finished answer. It does not disclose ranking, recency, or the historical toggle behavior.
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?
Four compact sentences, front-loaded with scope before exclusions, output caveat, and the clarification instruction. Every sentence carries information, though the domain enumeration is slightly list-heavy.
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, the description usefully explains that results are source candidates rather than answers, and it bounds the scope well. However, given 0% schema description coverage it leaves all three parameters undocumented, which is a meaningful gap for an agent deciding how to call it.
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% across all three parameters, and the description mentions none of them. It gives no guidance on how to shape 'query', why 'max_results' is capped at 5, or what 'include_historical' actually retrieves, so it fails to compensate for the coverage gap.
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 (Find) and a concrete resource (Roundup Q&A, Podcast and feature-article evidence) with the subject domains it covers. An agent can tell exactly what corpus is being searched, and there are no siblings to distinguish from.
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?
Explicitly lists out-of-scope requests (live weather, general advice, private data, credentials, service prices) so the agent knows when not to call it, and adds the instruction to clarify ambiguous requests. This is unambiguous routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
search_roundup_knowledgeSearch Japanese software and AI tools; read recorded facts with source links. Read-only.
Marketing, growth & SEO intel: 120+ practitioner sources, judged daily, with citable summaries.
Sales lists of local businesses in Japan with contacts, website type and contact forms
Japanese public-sector business opportunities for AI agents: tenders, subsidies, sanctions. x402.
Add one secure layer between your agents and this server.
