Search this knowledge base; returns matching chunks with distances.
Uses **exactly the same retrieval path as real conversations** — use it to validate the cutoff
and chunking: an empty result means this question will be judged "not covered" and the agent
will answer "not in the knowledge base".
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| kb_name | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the burden. It discloses that the tool uses exactly the same retrieval path as real conversations, adding context that results are aligned with actual agent behavior. It also clarifies empty result semantics, which is valuable behavioral information beyond the schema.
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 crisp sentences, front-loaded with the core action, followed by an important nuance. No filler or redundant 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?
Given the tool's simplicity, the description covers the essential usage and behavioral caveats. An output schema exists to define the return structure, so the description need not elaborate. It lacks explicit alternatives, but overall the context is sufficient.
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?
The schema has no descriptions (0% coverage), so the description should compensate. It implies that 'query' is the user question and 'kb_name' is the target knowledge base, but does not specify formats or whether kb_name is an ID or name. This adds minimal meaning beyond the schema, so a score of 3 is appropriate.
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's action ('Search this knowledge base') and result ('returns matching chunks with distances'), and distinguishes its purpose by noting it uses the same retrieval path as real conversations, positioning it for validation rather than general search.
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 explicit guidance to use it to validate cutoff and chunking, and explains the meaning of an empty result. However, it does not mention when to use alternative search tools like search_agent4_docs, so it lacks exclusions or alternatives.
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 are mostly distinct by domain and action. A few pairs like add_knowledge_file vs add_knowledge_text or build_knowledge_index vs patch_knowledge_index could cause confusion, but descriptions clearly differentiate them.
The vast majority follow a consistent verb_noun snake_case pattern (create_*, list_*, get_*, update_*). A few outliers like tenant_info, usage_stats, and page_context_stats are noun-first, deviating slightly from the otherwise uniform scheme.
With 50 tools, this is a very large surface that exceeds typical well-scoped server sizes. Even for a broad platform management API, the sheer number makes it heavy and potentially overwhelming, matching the '50+' extreme mismatch category.
The server covers creation, reading, updating, and listing for most resources but lacks any delete operations (no delete_agent, delete_knowledge_base, delete_skill, delete_share, delete_storyline, delete_page_context). This is a significant gap in lifecycle coverage that will force agents to work around missing functionality.