Search for contacts by person, role, tenure, industry, company headcount, company type, or recent job change using the API key owner's Sales Navigator connection.
| Name | Required | Description | Default |
|---|---|---|---|
| __requestBody | Yes | Request body |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds one meaningful behavioral fact: the search uses the API key owner's Sales Navigator connection, which clarifies data provenance and permission scoping. However, it does not go further to explain result pagination, limits, credential requirements, or output shape, and annotations do not clearly establish the read-only nature of the operation.
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?
A single sentence conveys the resource, the range of criteria, and the data source without any filler. It is front-loaded and every clause adds meaning.
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 search operation with a heavily self-documenting schema, the description is largely sufficient: it identifies the resource, criteria, and connection context. It could be stronger by naming the output type or return format, but the pagination parameters and tool name make the expected behavior reasonably inferable.
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%, so the many nested filter parameters and pagination fields are already fully documented in the schema. The description's high-level filter list adds orientation but no new semantic detail beyond what the schema 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 names a specific verb ('Search'), a clear resource ('contacts'), and the scope of the search dimensions ('person, role, tenure, industry, company headcount, company type, or recent job change'). It also distinguishes itself from enrichment and list-management siblings by framing this as a Navigator-backed contact search.
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 implies the tool's use case — searching Sales Navigator contacts by a defined set of criteria — but does not explicitly state when to prefer it over alternatives such as contacts-enrich_custom or contact_lists. There is no when-not-to-use guidance or mention of sibling exclusions.
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 have overlapping purposes, such as signals-firmographics vs companies-enrich_firmographics, findEmail vs contacts-enrich_work_email, and monitors vs signal_subscriptions vs market_signals. While descriptions add some context, an agent could easily select the wrong tool due to the high similarity in function.
Most tools use a resource_subresource-action pattern, but there are inconsistent separators: underscores within some names, hyphens in others (e.g., scoring-assignment-bulk-create), and several camelCase exceptions (findEmail, findEmailBatchGet, getContactResearchByExternalID). This mixed convention makes the tool set feel unpredictable.
With 119 tools, this server vastly exceeds the typical well-scoped range. Even for a comprehensive B2B data platform, the sheer number creates cognitive overload and increases the risk of incorrect tool selection.
The server covers an extensive range of operations: enrichment, lists, contacts, signals, subscriptions, monitors, and scoring. Nearly every resource has create, read, update, and delete or lifecycle equivalents, leaving very few practical gaps for the intended use case.
