Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
Scored across 3 tools
Each tool has a clearly distinct role: finding ranked solutions, comparing multiple tools, and producing a detailed security report. The cross-reference from compare_tools to find_solutions further reduces any risk of misselection.
All tool names follow a consistent verb_noun pattern with snake_case: compare_tools, find_solutions, get_trust_report. This makes the toolset predictable and easy for an agent to navigate.
Three tools is on the lean side for a discovery and security gateway, but each tool serves a meaningful and distinct purpose. The count is reasonable, though a slightly broader surface could be justified.
The core workflow of discover, compare, and inspect trust is well covered. Minor gaps exist, such as a general catalog listing or a lightweight tool-details endpoint, but agents can accomplish the primary tasks without dead ends.
Compare several indexed tools side by side on trust signals: trust score, security flags, publisher verification, category, and pricing tier. Pass 2-6 slugs. Fit depends on the specific problem - call find_solutions for ranking.
| Name | Required | Description | Default |
|---|---|---|---|
| slugs | Yes | Tool slugs to compare. |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden, and it does well by disclosing the exact comparison dimensions and constraining scope to 'indexed tools.' It does not cover error handling or invalid slugs, but the core behavior is clear and non-mutating.
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 no filler: the first states the tool's purpose and outputs, the second gives a usage routing hint. Every sentence earns its place.
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 an output schema exists, return-value details are covered. The description covers comparison fields, slug count limits, and an alternative tool, but could be more complete by differentiating get_trust_report.
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% and the schema description 'Tool slugs to compare' already documents the parameter. The description repeats the 2-6 limit but adds no new meaning beyond what the schema provides, so 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?
Description states a specific action ('Compare several indexed tools side by side') and names the comparison dimensions (trust score, security flags, publisher verification, category, pricing tier). This clearly distinguishes it from ranking-related siblings like find_solutions.
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 description explicitly directs agents to use find_solutions for ranking when fit matters, giving a clear alternative. It does not explicitly contrast with get_trust_report, but the comparison vs. ranking distinction is actionable enough for most cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Given a user's problem in natural language, return ranked solution recommendations (software platforms and MCP-connectable tools). Each result includes a semantic fit score, a trust/security score, any security flags, and a short rationale. Surface the flags to the user transparently.
| Name | Required | Description | Default |
|---|---|---|---|
| top_k | No | How many recommendations to return. | |
| problem | Yes | The user's problem or need, in their own words. | |
| max_pricing_tier | No | Optional ceiling: free, freemium, paid, or enterprise. |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the transparency burden. It discloses what the tool returns, that results are ranked, that trust and security scores are included, and that security flags must be surfaced transparently. It does not explicitly state non-mutating behavior or authentication needs, but the 'find' semantics make those less critical.
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 two sentences, front-loads the core function, and earns each sentence by explaining inputs, outputs, and the required flag-surfacing behavior. It contains no filler or redundant restatement of the tool name.
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 moderate complexity and the presence of an output schema, the description is largely complete: it covers the input type, ranked result format, scoring criteria, and transparency expectation. It could strengthen completeness by noting how top_k and max_pricing_tier shape results or by referencing sibling tools, but these are not essential for correct invocation.
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 schema already documents problem, top_k, and max_pricing_tier. The description adds value by explaining the scoring dimensions of results, but it does not add parameter-level meaning beyond the schema, so 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 specific verb ('return') and resource ('ranked solution recommendations'), and clearly identifies the input (user's problem in natural language) and the output fields (semantic fit score, trust/security score, flags, rationale). This distinguishes it from the sibling tools compare_tools and get_trust_report, which address comparison and trust details rather than initial discovery.
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 description gives clear context for when to use the tool: whenever a user expresses a problem in natural language and needs solution recommendations. It does not explicitly describe exclusions or alternatives, but the intended trigger is evident from the first sentence.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a detailed trust and security report for one indexed tool by slug: publisher verification, permissions requested vs actually needed (with the overreach highlighted), injection-scan verdicts on the tool description, and the trust score interpretation.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Tool slug, e.g. 'github-mcp'. |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral burden. 'Get' signals a read-only operation, and the listed report components—especially 'overreach highlighted' and 'trust score interpretation'—describe what the tool computes and returns. It does not discuss rate limits or auth, but for a read-only report tool this is a minor gap.
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?
One front-loaded sentence that starts with the action and resource, then uses a colon-delimited list to pack in the report contents. Every clause adds value and there is no filler or repetition.
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 single-parameter read tool with an output schema, the description covers the lookup key and the substantive contents of the report. It is not fully explicit about sibling-tool routing, but the core invocation details are sufficiently complete for an agent to call it correctly.
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 single slug parameter is already fully documented in the schema with 100% coverage and an example. The description only restates that the report is keyed 'by slug' and adds the 'indexed tool' constraint, which is helpful but not a major addition beyond the schema.
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 ('Get') and a specific resource ('detailed trust and security report' for 'one indexed tool by slug'), then enumerates the report's contents. The singular 'one indexed tool' clearly distinguishes it from siblings like compare_tools and find_solutions.
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 description makes clear it is the right choice when you need a trust/security report for a single specific slug. However, it does not explicitly name alternatives or state when to prefer compare_tools or find_solutions, relying on the 'one indexed tool' wording to imply the boundary.
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.
compare_toolsfind_solutionsget_trust_report
Add one secure layer between your agents and this server.
