Search d.cv talent profiles by free-text query (name, role, skills, location). Returns lightweight results with an id, title, and url. Use fetch to read one in full. (Standard connector search tool.)
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | What to look for, e.g. "senior react engineer in berlin" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the burden of behavioral disclosure. It states that results are lightweight and include id, title, and url, and implies a read-only operation. It does not cover pagination or rate limits, but for a simple search tool this is adequate.
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 three short sentences plus a parenthetical, all providing useful information with no redundancy. It is front-loaded with the search purpose and returns format.
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?
The tool is simple with one parameter and no output schema, and the description covers its functionality, return format, and a recommended next step. This is sufficient for an agent to invoke it correctly.
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 single parameter 'query' is fully described in the schema, and the tool description adds meaningful context about what can be searched (name, role, skills, location). This goes beyond the schema's example, justifying a score above baseline.
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 searches talent profiles by free-text query, specifying searchable fields (name, role, skills, location). It is specific and concise, though it does not explicitly differentiate from sibling 'search_talent', so slightly below 5.
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 gives clear context for using the tool (free-text search) and directs users to 'fetch' for full results. However, it does not provide explicit when-not-to-use guidance or mention alternatives like 'search_talent', leaving usage boundaries implicit.
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.
There is significant overlap between tools: 'search' and 'search_talent' both search profiles with similar functionality, and 'fetch' and 'get_profile' both retrieve a full profile by handle. This creates ambiguity about which tool to use for a given task.
Naming conventions are inconsistent: some tools use bare verbs ('fetch', 'search'), some use verb-noun ('get_profile', 'save_search'), and one uses a multi-word phrase ('get_open_to_work'). The pair 'search' and 'search_talent' also breaks any consistent pattern.
Seven tools is a well-scoped number for a talent search server. It's not overwhelming or too sparse, and each tool has a place in the candidate discovery workflow.
The tool set covers the core workflow: searching, retrieving full profiles, filtering open-to-work candidates, adding to shortlists, and saving searches. However, the duplicate fetch/get_profile pair suggests one could be replaced with something like listing or managing shortlists.
