get_contactReopen someone this account found before, by the person ID find_contact returned, their email or their LinkedIn address. Free. Answers not_found for anyone the account has not found.
| Name | Required | Description | Default |
|---|---|---|---|
| No | |||
| person | No | A person in Nameclick's store, as find_contact returns it. | |
| No | A LinkedIn profile's address, such as https://www.linkedin.com/in/someone. |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Output schema / definitions / Card / properties / email / descriptionPrevious value: -"Their email address on record, or null when none is."New value: +"Their email address on record, or null when none is, or when personal_address says one is held back."Output schema / definitions / Card / properties / personal_addressAdded value: +{
+ "description": "A personal address such as Gmail is on record, which shows in the extension or on a paid plan; until then email is null.",
+ "type": "boolean"
+}Output schema / definitions / Card / properties / publishedRemoved value: -{
- "anyOf": [
- {
- "additionalProperties": false,
- "properties": {
- "address": {
- "format": "email",
- "maxLength": 254,
- "pattern": "^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$",
- "type": "string"
- },
- "where": {
- "const": "github",
- "type": "string"
- }
- },
- "required": [
- "address",
- "where"
- ],
- "type": "object"
- },
- {
- "type": "null"
- }
- ],
- "description": "An address the person publishes on their own profile, shown as theirs."
-}Output schema / definitions / Card / requiredPrevious value: -[
- "person",
- "name",
- "title",
- "employer",
- "photo",
- "linkedin",
- "links",
- "email",
- "published",
- "observed",
- "matched",
- "thin",
- "sourcey",
- "details",
- "history",
- "company"
-]New value: +[
+ "person",
+ "name",
+ "title",
+ "employer",
+ "photo",
+ "linkedin",
+ "links",
+ "email",
+ "personal_address",
+ "observed",
+ "matched",
+ "thin",
+ "sourcey",
+ "details",
+ "history",
+ "company"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavior: the call is free (no credit cost) and returns not_found for people outside the account's history, which tells the agent how to interpret an empty result.
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?
Three short sentences with no waste: what it does, the accepted identifiers, cost, and error semantics. The identifier list and the 'Free' cost note are front-loaded where the agent needs them.
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?
An output schema exists and annotations already cover safety, so the description only needs to frame purpose, cost and error handling, which it does. The one remaining hole is whether at least one identifier must be supplied given that all three parameters are optional.
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 67% and both 'person' and 'linkedin' already carry descriptions, so the schema does most of the work. The description adds useful provenance (the person ID is what find_contact returned) but never clarifies that zero parameters are required or whether the three identifiers are alternatives, so the key ambiguity about what to supply is left unresolved.
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?
States a specific verb ('Reopen') and resource ('someone this account found before'), and enumerates the three lookup keys. The phrase 'found before' plus the reference to find_contact clearly separates this retrieval-of-known-person tool from the discovery sibling.
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?
Gives a clear usage context: it is for people the account has already found, and 'Answers not_found for anyone the account has not found' implicitly routes the agent to find_contact first. It stops short of an explicit 'use find_contact instead when the person is new' exclusion, so it falls shy of a 5.
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.