get_epss_scoreGet the EPSS (Exploit Prediction Scoring System) score for a CVE. Returns the probability of exploitation in the next 30 days and percentile ranking.
| Name | Required | Description | Default |
|---|---|---|---|
| cve_id | Yes | CVE identifier |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the tool's safety profile is known. The description adds value by specifying the return values (probability and percentile), but does not cover potential caveats like data freshness or error 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?
The description is two sentences long, front-loads the primary purpose, and contains no redundant information. Every word contributes to understanding the tool's function.
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 one-parameter read tool with no output schema, the description adequately explains the return format (probability and percentile). A mention of potential error behavior when the CVE is not found would make it fully complete, but it is otherwise sufficient.
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 input schema fully documents cve_id with a pattern and description (100% coverage). The description aligns with the schema ('for a CVE') but adds no extra meaning beyond what the schema already provides.
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 tool retrieves the EPSS score for a CVE, with specific output context (probability within 30 days and percentile ranking). This distinctively separates it from sibling tools like get_cve_details or get_exploits.
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?
No explicit guidance is given on when to use this tool versus alternatives. The description implies usage for EPSS scores, but does not mention when not to use it or name alternative tools, leaving the agent to infer context from sibling names.
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.
Most tools have clearly distinct purposes, but a few pairs overlap: get_current_step vs get_progress, search_cve vs search_by_product, and describe_capabilities vs get_my_capabilities. The descriptions provide enough detail to differentiate them, but agents could still occasionally misselect.
Names overwhelmingly follow a verb_noun snake_case pattern (get_*, list_*, search_*, start_*, etc.). Minor deviations like 'diff' and 'search' (single-word) and 'batch_search' (compound modifier) are predictable and don't disrupt the overall consistency.
With 30 tools, the server is on the heavier side. The broad scope (legal intelligence, CVE data, full workflow engine) justifies many tools, but some are internal or niche (probe_corpus, recommend_subagents) and could be hidden. It's borderline between well-scoped and excessive.
The legal and CVE domains are well-covered: search, provision lookup, validation, diff, coverage, and detailed CVE enrichment. Workflow management is end-to-end. However, get_regulatory_deadlines is referenced by get_regulatory_intelligence_status but not exposed in the toolset, leaving a notable gap.