vector_search_usecasesSemantic vector search for AI use cases using the meaning of the query text.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum results requested. Public previews return at most 3; personal-key access permits up to 20. | |
| query | Yes | Natural-language query. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / limit / descriptionAdded value: +"Maximum results requested. Public previews return at most 3; personal-key access permits up to 20."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds that the tool performs semantic vector search over AI use cases, but it does not disclose ranking behavior, similarity thresholds, or what happens with irrelevant queries. This is acceptable but not rich.
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 a single concise sentence with no filler. It is slightly redundant with the title ('semantically similar' vs 'semantic vector search' and 'meaning'), but it remains efficient and front-loads the core mechanism.
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 simple two-parameter, read-only tool, the description plus schema is mostly sufficient. However, there is no output schema and no mention of return shape or ranking, and the description's 'AI use cases' vs the title's 'AI deployments' introduces a minor ambiguity that could confuse an agent.
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%, so the parameters query and limit are fully documented in the schema. The description only reinforces that query is interpreted by meaning, which does not add meaningful new information beyond the schema. Baseline 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 states a clear mechanism ('semantic vector search') and a target resource ('AI use cases'), reinforced by the title 'Find semantically similar AI deployments'. It is specific about using query meaning, but it does not explicitly contrast itself with hybrid_search_usecases or search_usecases, relying on sibling names to imply the difference.
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 phrase 'using the meaning of the query text' implies the tool is for semantic rather than keyword matching, so an agent can infer when it might apply. However, there is no explicit guidance on when to prefer this over hybrid_search_usecases or search_usecases, nor any exclusion criteria.
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.
Three of the four tools are search variants with overlapping behavior: search_usecases and hybrid_search_usecases both use hybrid ranking, and vector_search_usecases partially overlaps with the default semantic behavior. The descriptions provide some clues (filters vs. natural-language), but the boundary between the search tools remains unclear.
The search tools follow a clean pattern of [modifier_]search_usecases, and get_usecase_details uses a standard verb_noun form. The only minor deviation is singular 'usecase' in get_usecase_details versus plural 'usecases' in the search tools.
Four tools is a reasonable size for a focused use-case hub. Having three search variants is slightly redundant, but the count is still well within an appropriate scope.
The set covers the core retrieval workflow: search across multiple modes and fetch full details by ID. Minor gaps include the absence of a browse/list-all tool or explicit pagination, but agents can likely accomplish the intended tasks.