Start an async deep-infrastructure OSINT investigation for a query (domain, IP, or org). Operator-deploy only; degrades to info when unprovisioned. Returns an investigationId immediately — poll with osint_investigation_status.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate this tool is not read-only (readOnlyHint: false), not idempotent (idempotentHint: false), and not destructive (destructiveHint: false). The description adds behavioral context: it is async (returns immediately), operator-deploy only, and degrades to info when unprovisioned. No contradiction with annotations. The bar is slightly lowered due to annotation coverage, and the description adds useful behavioral traits beyond what annotations provide.
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 concise at 23 words across two sentences. The first sentence clearly states the purpose and input types. The second covers behavioral notes and follow-up. No unnecessary filler. It loses a point because the operator-deploy and unprovisioned behavior might be better presented as a separate note or structured annotation, but overall efficient.
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?
Given the simple schema (1 param, no output schema, no nested objects) and rich sibling context, the description adequately covers: what action is performed, what inputs are accepted, async behavior, deployment restrictions, and how to retrieve results. The only minor gap is not detailing what the returned investigationId looks like or what the status polling tool requires. Still, for a start tool with clear polling counterpart, this is 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?
Schema coverage is 0%, so the description must compensate for the undocumented 'query' parameter. The description does state that query can be a 'domain, IP, or org', which adds semantic value beyond the raw schema (which only specifies maxLength and minLength). However, it does not specify the exact formats expected (e.g., full URL vs domain only, IPv4 vs IPv6, organization name vs identifier). Baseline 3 for zero coverage is partially compensated by the type description but could be more precise.
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 starts an async deep-infrastructure OSINT investigation for a domain, IP, or org. It specifies the verb 'Start' and the resource 'OSINT investigation', distinguishing it from sibling tools like osint_investigate_domain_start and osint_investigate_email_start which focus on different aspects. However, it does not explicitly differentiate itself from osint_investigate_supply_chain_start which also covers orgs.
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 provides clear guidance: it is operator-deploy only, degrades to info when unprovisioned, and returns an investigationId immediately for polling with osint_investigation_status. This tells the agent when to use it (for async deep investigations) and how to follow up. However, it does not explicitly state when not to use it versus alternatives like osint_investigate_domain_start.
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, with detailed descriptions that help differentiate overlapping areas (e.g., check_dane vs check_dane_https). However, there are sets of similar tools (brand audit, OSINT, polling) that could cause confusion if descriptions are not carefully read.
The naming is mostly readable but inconsistent: many check_* tools follow a verb_noun pattern, but there are also noun_verb names (scan_domain, cymru_asn), bare verbs (generate), and varied patterns for async operations (discover_brand_domains_start vs discover_brand_domains).
With 80 tools, the server feels overstuffed. It covers multiple domains (DNS, email, brand, OSINT, M365) that could benefit from separation. The high number includes many polling/status tools that add overhead.
The server covers core DNS and email security checks thoroughly, including many edge cases (e.g., BIMI, MTA-STS, subdomain takeover). However, there are gaps like lack of direct DNS record management and some OSINT tools are restricted to operator deployment, leaving agents with dead ends.
