Run Saina decision endpoints and retrieve decisions via MCP.
Scored across 1 tool
With only a single tool in the set, there is no possibility of overlap or misselection between tools. An agent always knows which tool to call, though the single tool itself internally multiplexes many resource types via id.
The lone name 'search' is a clear, lowercase verb and there are no competing conventions to conflict with it. It is slightly underspecified as a bare verb without a resource noun, but with one tool this is not confusing.
The description names roughly fourteen distinct resource types (endpoints, datasets, collections, records, models, deployments, providers, loops, evals, experiments, metric definitions, versions, decisions), yet the server exposes only one tool. That is far too thin for the apparent scope of the domain.
The surface offers only exact-id lookup — no list/browse, no get-by-name, no create/update/delete across any resource type. Retrieval by exact id partially works around this, but there are no lifecycle operations at all, leaving the domain severely under-covered.
Search the account across endpoints, datasets, collections, records, models, deployments, providers, loops, evals, experiments, metric definitions, versions, and decisions by exact id. A decision id can match both the decision and its stored record. A session sees every type. A key sees only types its read scopes allow.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | ||
| limit | No | ||
| types | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover safety (readOnlyHint=true, openWorldHint=false), and the description adds real context beyond them: a decision id can match two results, and visibility is scope-dependent for keys vs sessions. It stops short of describing result shape or what happens when limit truncates matches.
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?
Front-loaded with the verb and scope, then the two behavioral caveats. The long type enumeration is dense but genuinely informative rather than filler; the only waste is that it duplicates information an agent could infer.
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 only safety annotations, the description should explain more of the contract. It covers visibility scoping and the dual-match edge case well, but omits limit/truncation behavior and whether an empty or missing 'q' returns everything.
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%, so the description must carry the load. It hints that 'q' is an exact id and enumerates the valid types, but 'limit' is never mentioned and there is no guidance on the 'types' string format (single, comma-separated, etc.). Two of three parameters remain effectively undocumented.
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) plus the full set of resource types it spans and the matching mode (exact id). That is well beyond a tautology. It loses a point because the schema's free-form 'q' string suggests fuzzy/text querying while the description insists on 'exact id', leaving the actual matching semantics ambiguous.
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?
Implies the usage context ('by exact id') and explains the session-vs-key visibility difference, but never says what to do when you don't have an exact id, nor how 'q' should be combined with 'types'. With no sibling tools there is nothing to route to, so the guidance is implied rather than explicit.
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.
searchEvidence-linked MCP selection and non-executing Safe-Call review; surfaces unknowns.
Hosted MCP for denial, prior auth, reimbursement, workflow validation, batch scoring, and feedback.
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
MCP server for the BuyerSense API. Get buyer signals from any MCP client.
Add one secure layer between your agents and this server.
