Verify a vuln report's file/line/function claims against a real GitHub repo.
Scored across 1 tool
With only one tool, there is no possibility of overlap or misselection, and the tool's purpose is stated with unusual precision (it checks concrete cited claims, explicitly not vulnerability validity). An agent cannot confuse it with anything else in this surface.
The single name, check_vuln_report, follows a clean snake_case verb_noun convention and reads clearly. It is consistent by construction, though a one-tool set cannot demonstrate a repeatable pattern across the surface.
A single tool is thin even for a narrow purpose, and the server name 'triageshield' implies broader triage activity than one check operation. It is borderline rather than mismatched, since claim verification is genuinely a single focused check.
For the narrow claim-verification task the surface is reasonably covered, but the 'triage' framing suggests missing operations: no severity/exploitability assessment, no summarization of which claims failed, and no repo-inspection helper. Agents hitting those needs will dead-end.
Verify a vulnerability report's concrete, checkable claims (file paths, file.py:123 line citations, function names) against a real GitHub repo's current default-branch state. Does NOT judge whether the described vulnerability is real or exploitable -- it only checks whether the files/lines/functions cited actually exist, which is the exact 'AI slop' failure mode (hallucinated specifics) that makes up a real share of auto-generated vuln reports. A PLAUSIBLE verdict means the claims check out, not that the vulnerability is confirmed real.
| Name | Required | Description | Default |
|---|---|---|---|
| repo | Yes | A github.com/owner/name URL for the repo the report claims to be about | |
| report | Yes | The vulnerability report text to check |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does substantial work: it discloses the comparison target (current default-branch state, implying the check is against live/HEAD rather than historical code), the scope boundary (existence of cited artifacts, not exploitability), and the semantics of the 'PLAUSIBLE' verdict. It does not cover auth/rate-limit or error behavior, but the core behavioral contract is unusually well articulated.
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?
Three sentences, front-loaded with the core action, with each subsequent sentence adding a distinct clarification (scope exclusion, failure-mode motivation, verdict semantics). Dense and largely waste-free, though the parenthetical explanation of the failure mode is slightly verbose.
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?
There is no output schema, so the description bears the burden of explaining return semantics; it explains the key 'PLAUSIBLE' verdict but does not enumerate the other possible verdicts (e.g. what a negative/refuted result is called). For a two-parameter, no-annotation tool this is nearly complete, with only the verdict range left implicit.
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% and both parameters are documented in-schema, so the baseline is 3. The description adds context about the nature of the 'report' parameter (concrete claims like file paths, line citations, function names) and requires 'repo' to be a github.com/owner/name URL is already in schema, but it does not extend syntax or format guidance 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?
The description states a precise verb+resource ('verify a vulnerability report's concrete, checkable claims') and clarifies the exact object of verification (file paths, `file.py:123` citations, function names vs. current default-branch state). It also distinguishes itself from what an agent might assume it does by ruling out exploitability judgment. An agent can tell immediately what this tool is and is not.
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 this tool applies—checking auto-generated vuln reports for the 'AI slop' hallucinated-specifics failure mode—and explicitly carves out when its verdict should not be over-read ('PLAUSIBLE... not that the vulnerability is confirmed real'). No sibling tools exist to route between, so the absence of an explicit alternative is not a gap, but there is no stated precondition (e.g. report format expectations) either.
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.
check_vuln_reportIndependent static verification for exact immutable public GitHub commits.
Audit GitHub repos for malicious and supply-chain code before you depend on them.
Audit and repair any public GitHub repo. Free survey; paid source, unified diffs and a pull request.
Screens public GitHub repos and PRs to generate risk maps, findings, and merge-readiness signals.
Add one secure layer between your agents and this server.
