keap_create_taskCREATE a task (follow-up / to-do), optionally linked to a contact. Keap: POST /tasks.
| Name | Required | Description | Default |
|---|---|---|---|
| extra | No | Any other Keap fields to merge into the request body verbatim. | |
| title | Yes | The task title. | |
| due_date | No | Due date/time, ISO 8601 (e.g. 2026-08-01T17:00:00Z). | |
| contact_id | No | Id of a contact to link the task to. | |
| description | No | A longer description / notes for the task. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare destructiveHint=true, while the description says 'CREATE a task' and references POST /tasks. Creating a task is not destructive, so the description contradicts the annotation. No additional behavioral context such as side effects or required permissions is provided.
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 with no filler; the core action and endpoint are front-loaded and every sentence adds value.
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?
There is no output schema, the tool has 5 parameters, and the annotations conflict with the described behavior. The description does not clarify what the response will contain or reconcile the destructiveHint inconsistency, leaving an agent without enough context to fully understand the operation's effects.
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 schema fully documents title, due_date, contact_id, description, and extra. The description only adds that the task may be linked to a contact, which duplicates contact_id's schema description, and does not provide meaningful new parameter semantics.
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 (CREATE), resource (task), and domain (follow-up / to-do), plus the exact endpoint. This distinguishes it from sibling tools like keap_create_contact or keap_get_task without requiring the schema.
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 use when a new task should be created, and optionally linked to a contact, but it does not explicitly state when not to use it or mention alternatives like keap_get_task, keap_list_tasks, or keap_update_contact. Usage guidance is only 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.
Each tool targets a clearly distinct resource and action: list_* tools are separated by entity, get_* tools retrieve individual records, and create_/update_/apply_ tools perform unique mutations. There is no meaningful overlap or ambiguity between tools.
All tools consistently use the keap_ prefix followed by a verb_noun pattern, such as list_contacts, get_company, create_task, and update_contact. The naming convention is uniform across all 18 tools.
At 18 tools, the count falls into the borderline 16-25 range and feels somewhat heavy for a single server. Each tool does have a distinct purpose, but the set is larger than ideal and includes many read-only list/get operations.
Contacts and tasks have reasonable lifecycle coverage, but most other entities such as opportunities, companies, orders, products, and subscriptions are read-only. Notable operations like removing a tag, updating/deleting tasks, and updating opportunities are missing, creating potential dead ends.