contacts_createSave your own contacts or organizations. Free. Existing contacts are matched and kept, never duplicated.
| Name | Required | Description | Default |
|---|---|---|---|
| contacts | Yes | Contacts to save; each needs an email, LinkedIn URL, website or organization ID |
| Name | Required | Description | Default |
|---|---|---|---|
| saved | Yes |
Changes observed during successful MCP inspections.
Input schema / properties / contacts / items / properties / organizationId / descriptionPrevious value: -"From /organizations/search"New value: +"From organizations_search"Input schema / properties / contacts / descriptionAdded value: +"Contacts to save; each needs an email, LinkedIn URL, website or organization ID"Output schema / (root)Previous value: -nullNew value: +{
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
+ "additionalProperties": false,
+ "properties": {
+ "saved": {
+ "type": "number"
+ }
+ },
+ "required": [
+ "saved"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this is a non-read-only, non-destructive, closed-world write. The description adds behavior annotations do not carry: it is free (useful given the credits_get sibling) and it is idempotent-by-matching ('matched and kept, never duplicated'). It does not describe partial-failure or per-item error behavior for batch submissions.
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?
Two short sentences, action and scope first, then the two behavioral facts that actually matter (cost, dedup). No filler whatsoever.
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?
Output schema and annotations carry the return-shape and safety burden, and the description covers the two facts structured fields cannot express. Only the batch semantics (up to 1000 items, partial failures) are left unaddressed.
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% and the array item field set, min/max items, and the organizationId provenance note are all documented in the schema. The description adds nothing about parameter format, so baseline 3 applies.
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 (Save) and resource (contacts or organizations), and the phrase 'your own' signals it differs from the lookup/search siblings. It is clear, but it never names an alternative tool to contrast against, so differentiation is inferred rather than stated.
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?
There is no explicit when-to-use or when-not-to-use guidance and no named alternative among siblings such as organizations_search or contacts_list. The word 'own' faintly implies this is for user-supplied contacts rather than enriched data, but the agent must infer that.
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.