search_semanticSemantic search over scans (paginated).
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | ||
| limit | No | ||
| query | Yes | ||
| threshold | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnly, idempotent, and non-destructive behavior. The description adds only the pagination detail, providing minimal extra context. No information on authentication, rate limits, or result ordering is given.
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, compact sentence that conveys the essential function without wasted words. It is appropriately concise and front-loaded.
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?
Despite having an output schema and annotations, the description lacks critical usage context: what semantic search means, how the threshold affects results, and when to prefer this over other search tools. The pagination note is a small addition, but overall the tool is incompletely described.
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 0%, and the description does not explain the meaning of 'query', 'threshold', 'page', or 'limit' beyond the word 'paginated' which hints at page/limit. The required query parameter and threshold score are left unexplained, providing little semantic value.
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 'Semantic search over scans (paginated)' clearly identifies the action (search), the resource (scans), and a distinguishing feature (semantic, paginated). It is specific and differentiates from sibling tools focused on other search types.
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 guidance is provided on when to use semantic search versus the many other search tools (e.g., search_scans, search_by_ip). The description does not mention alternatives or exclusions, leaving the agent to infer usage.
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.
Many tools overlap in purpose, particularly the JS fingerprint search functions (e.g., search_js_fingerprint_by_md5 and search_jsfingerprints_by_md5) which are nearly identical. The large number of get_* and search_* tools for various statistics also creates boundary ambiguity.
The verb_noun pattern is mostly followed, but there are significant inconsistencies: 'jsfingerprints' vs 'js_fingerprints' vs 'js_fingerprint', and the occasional use of 'find' instead of 'search' (e.g., find_js_fingerprint_similar_by_hash). This mixed style makes it hard to predict tool names.
With 128 tools, the server is severely over-scoped. Many tools could be combined (e.g., all search_jsfingerprints_by_* variants) or parameterized. The sheer number overwhelms an agent and suggests poor API design.
The core URL scanning workflow (submit, retrieve results, search, analyze) is well covered, including detailed sub-analyses like malware, YARA, and JS fingerprints. Minor gaps include no scan cancellation or user-specific scan listing, but overall coverage is strong.