export_findings_sarifExport the active project's security findings as a SARIF 2.1.0 document — the format GitHub Code Scanning and comparable CI tools ingest. Defaults to open findings so the export reflects the current posture. Requires project context.
| Name | Required | Description | Default |
|---|---|---|---|
| status | No | Only findings in this status: 'open' (default), 'inProgress', 'fixed', 'falsePositive', 'acceptedRisk' or 'duplicate' |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already signals that the operation is read-only, and the description adds context about default filtering and the need for project context. It does not disclose any side effects because none exist, and it appropriately avoids repeating the annotated read-only status.
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 concise sentences with no redundant wording. It front-loads the core action and output format, then adds a brief note on default behavior and a prerequisite, making it easy to parse.
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 export tool, the description covers the necessary invocation details: what is exported, in what format, the default filter, and the context requirement. The output type is implied by the SARIF format, so no separate output schema is needed.
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 schema fully describes the only parameter ('status') with allowed values and a default, and the description reinforces the default ('Defaults to open findings') and explains why that default is meaningful ('reflects the current posture'). This gives the agent complete understanding of the parameter's behavior.
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 clearly states the action ('Export'), the object ('the active project's security findings'), and the output format ('SARIF 2.1.0 document'). It also explains the practical purpose by noting the format is what GitHub Code Scanning and comparable CI tools ingest, distinguishing it from general findings retrieval tools like get_security_findings.
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 explains default behavior ('Defaults to open findings') and a prerequisite ('Requires project context'), giving the agent useful invocation guidance. However, it does not explicitly contrast this tool with alternative export or findings-listing tools, though the purpose is clear enough to infer the appropriate use case.
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.
The tools are mostly distinct with clear descriptions. Some pairs like get_header_policies vs get_resolved_headers or get_environment_verification vs get_monitoring_sync_status could be slightly confusing, but the descriptions clarify scope and purpose.
All tools follow a consistent snake_case verb_noun pattern (get_, list_, create_, update_, manage_, etc.). Even the few bare verbs like 'search' and 'set_context' are consistent with the naming scheme.
With 165 tools, the server is extremely heavy. This far exceeds the 'too many' threshold of 25+, making it difficult for an agent to navigate and select the right tool efficiently.
The tool surface covers a very broad API lifecycle domain: specs, environments, test cases, monitors, mock servers, security, governance, documentation, and team management. Read and write operations are present across most areas, with no obvious missing core functionality.