List, create, rename, or delete portfolios (folders that organize projects). Supports nesting and searching.
List, create, rename or delete portfolios (the folders projects live in).
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Required for create and update. | |
| limit | No | list only. | |
| action | Yes | ||
| offset | No | list only. | |
| search | No | list only. | |
| parent_id | No | Nest a portfolio under another one. | |
| portfolio_id | No | Required for get, update and delete. |
Changes observed during successful MCP inspections.
v0.2.2Input schema / properties / parent_id / anyOfAdded value: +[
+ {
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / parent_id / typeRemoved value: -[
- "integer",
- "null"
-]v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It implies a destructive delete but says nothing about what happens to projects inside a deleted portfolio, whether nesting via parent_id is validated, or what permissions are required — a significant gap for a delete-capable tool with zero annotation coverage.
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?
One sentence, front-loaded with the action set, and the parenthetical definition of 'portfolio' earns its place by disambiguating from the project tools. Zero filler.
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 7-parameter multi-action CRUD tool with no annotations and no output schema, the description is minimum viable: it names the operations but omits 'get', gives no return or pagination context for list, and no delete side effects. An agent could call it, but not confidently.
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 86%, so the schema already documents name, portfolio_id, limit, offset, search and parent_id. The description adds no syntax, format, or interaction detail beyond what the schema provides, 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 specific verbs (list, create, rename, delete) against a named resource and defines the resource parenthetically as 'the folders projects live in', which separates it from siblings like weeek_manage_projects. It loses a point because the action enum includes 'get' and 'update' but the description only names 'rename'/'delete', so one supported action goes unmentioned.
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?
No when-to-use guidance, no prerequisites, and no named alternative among the many sibling manage_* tools. The only routing signal is the verb list itself, leaving the agent to infer the context from the action enum.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.