Searches a project's knowledge base for relevant context using Trove's hybrid search engine, helping retrieve information for coding tasks.
Search project knowledge for relevant context. Uses Trove's hybrid search engine.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The search query. | |
| top_k | No | Max results. Default: 10. | |
| client | Yes | Trove client name (project). |
Changes observed during successful MCP inspections.
v2.4.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full behavioral burden. It implies a read operation and names a 'hybrid search engine', but discloses nothing about permissions/auth, ranking behavior, result shape, or whether top_k is capped; a hybrid semantic+lexical search merits at least a note on how results are ranked or returned.
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 with the core purpose front-loaded and no filler. The second sentence on the hybrid engine adds a small amount of ranking context but is not strictly necessary.
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 and no annotations, the description should convey what results look like and how they are ranked. It omits return format and any scoping/auth notes, leaving a meaningful gap for an agent trying to interpret results.
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 coverage is 100%, so query, top_k, and client are already documented in the schema, which sets the baseline at 3. The description adds no extra meaning (e.g., what 'client' project scope entails or relevance of top_k) beyond what the schema already provides.
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) and resource (project knowledge) with a stated goal (relevant context), scoped by a project/client. Clear enough on its own, but it does not distinguish itself from the many sibling search tools (trawl_search, trawl_memory_search, trawl_search_entities) in the environment.
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?
There is no explicit when-to-use, when-not-to-use, or alternative guidance. With dozens of overlapping search siblings, an agent is left to infer when mullet_search is the right pick over trawl_search or trawl_memory_search.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.