Read-only search over the public Sikaru documentation: managed agents, inference, evals and traces.
Scored across 1 tool
There is only one tool, so there is no possibility of misselection or overlapping purpose. The single tool's purpose (searching Sikaru docs) is clearly stated.
The lone tool uses a clean camelCase verb_noun pattern (searchDocs) that reads naturally and matches the server's domain. With a single tool there is no convention mixing to penalize.
A single search tool is a thin surface for a documentation server; agents cannot list pages, fetch a full doc by URL, or browse sections. It is functional but borderline under-scoped.
Search covers the primary lookup workflow, but there is no companion operation to retrieve a full page or follow a returned source URL, which search results imply is a likely next step. Minor but notable gaps for a docs-access server.
Search the documentation at https://docs.sikaru.ai. Returns relevant doc passages with source URLs.
| Name | Required | Description | Default |
|---|---|---|---|
| topK | No | How many results to return (default 8, max 20) | |
| query | Yes | The search query to run against the docs |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and a title, so the safe-read profile is covered by structured data. The description adds that results are passages with source URLs, which is genuinely useful behavioral context, but it is silent on ranking, freshness, empty-result behavior, or limits beyond topK.
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?
Two short sentences, zero filler, with the resource identity and the return shape both front-loaded. Nothing could be removed without losing information.
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?
For a two-parameter read-only search tool with no output schema, the description covers the essential contract: what is searched and what is returned. The only meaningful gap is doc-corpus scope and result-quality caveats, which are minor at this complexity.
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%, and both parameters (query, topK with default 8 and max 20) are fully documented in the schema. The description adds no further meaning about query syntax, natural-language vs keyword matching, or how topK affects relevance, 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?
The description pairs a specific verb ("Search") with a specific resource ("the documentation at https://docs.sikaru.ai") and states what comes back ("relevant doc passages with source URLs"). It is unambiguous, though it does not say what the documentation corpus actually covers, leaving the agent to infer topical scope.
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?
Usage is only implied: the tool searches docs.sikaru.ai, so an agent can infer it should be used for product/documentation questions. There is no explicit guidance on when to prefer it over another approach, no note that it is scoped only to this site, and no stated preconditions.
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.
searchDocsSearch published MkSaaS documentation. Read-only and public.
Read-only search over the aidata.stream documentation, blog, changelog, pricing and FAQ.
Search and read the public Applivery docs (MDM & app distribution). Read-only, no auth.
Search and fetch AgendaForge public documentation and marketing content. No authentication needed.
Add one secure layer between your agents and this server.
