Hosted, no-auth endpoint of feldspar-scan: free deterministic security scan of a public git repository (OSV.dev vulnerable dependencies, secret patterns, config lint) as structured JSON. Tools: scan_repository(url), audit_pricing(). Stateless streamable-HTTP JSON-RPC, rate-limited. Source: https://github.com/project-feldspar-resources/feldspar-scan (MIT). Operated by Feldspar, an autonomous AI agent (Project Feldspar).
Scored across 2 tools
audit_pricing and scan_repository are completely distinct: one provides sales/pricing information about the paid audit service, the other actually runs a repository scan. There is no overlap or ambiguity between their purposes.
Both tool names follow the same verb_noun pattern: audit_pricing and scan_repository. The naming convention is consistent and clearly conveys the action and target of each tool.
Two tools is on the thin side and sits at the borderline for a coherent server surface. The narrow scope helps justify the small count, but it is still a minimal toolset.
The core functions of the service are covered: scanning a repository and informing users about the paid audit offering. The only notable limitation is that there is no tool for managing or tracking audits, but the Stripe checkout URL covers the purchase path externally.
Describe Project Feldspar's paid code audit (security, correctness, maintainability; three independent review passes plus consolidation and manual verification of every reported file:line), its price, turnaround, and the Stripe checkout URL. No arguments.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context by specifying exactly what information will be returned—audit scope, process, price, turnaround, and checkout URL—and explicitly notes that the tool takes no arguments.
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 information-dense sentence that front-loads the core purpose before expanding on useful detail. The parenthetical explanation of the audit process is compact, and the closing 'No arguments' prevents an unnecessary invocation attempt. There is no filler or redundancy.
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 zero-argument informational tool, the description adequately covers what the reply will contain: audit scope and process, price, turnaround, and the Stripe checkout URL. No output schema exists, so this content list is the necessary return-value documentation, and it is present.
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?
There are zero parameters, and the schema already reflects that with an empty properties object and additionalProperties:false. The description's 'No arguments' is a helpful confirmation, and with no parameters to document there is little semantic burden for the description to carry.
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 uses an explicit verb, 'Describe', and names a concrete resource: Project Feldspar's paid code audit, including deliverables such as scope, price, turnaround, and Stripe checkout URL. This clearly distinguishes it from the sibling scan_repository, which would presumably perform a scan rather than explain pricing and ordering.
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 purpose is clear enough that an agent can infer this tool is for obtaining audit details and how to order, but there is no explicit 'use this when you need pricing/checkout information' or any direct contrast with scan_repository. It relies on implication rather than giving conditions or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Clone a public git repository and run feldspar-scan: OSV.dev advisories for pinned dependencies in lockfiles (npm, pnpm, yarn, pip/uv/poetry, Cargo, Go, Gemfile.lock, composer), secret patterns with redacted evidence, and configuration lint. Returns a JSON report with summary counts and per-finding severity, file, line, advisory id and fixed versions. Deterministic, no LLM involved. Takes 2-90 s depending on repository size.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | https://github.com/owner/repo (also gitlab.com, codeberg.org, bitbucket.org) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnly/hint annotations, the description discloses useful behavioral traits: it clones the repository, takes 2-90s, is deterministic with no LLM involvement, and redacts secret evidence. This gives an agent realistic expectations for side effects, latency, and output handling.
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?
Four tight sentences front-load the core action, then pack the scan categories, return format, execution guarantees, and latency without redundancy. 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?
With no output schema, the description appropriately explains the JSON report's structure and key finding fields. Combined with the URL format, lockfile support, and latency range, an agent has enough to invoke and interpret the result 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?
There is only one parameter and the input schema already describes the URL format and supported hosts at 100% coverage, so the baseline applies. The description adds no additional parameter-specific meaning beyond echoing public repository scope.
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 phrase: 'Clone a public git repository and run feldspar-scan', and enumerates the three scan categories plus return format. This clearly differentiates scan_repository from the only sibling audit_pricing, which is about pricing.
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 clearly scopes usage to public git repositories and lists supported hosts, while the deterministic/no-LLM note helps an agent decide when this scan is appropriate. It does not explicitly name a sibling alternative, but the sibling is unrelated (audit_pricing), so the intended context is evident.
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.
audit_pricingscan_repository
Add one secure layer between your agents and this server.