Retrieve a saved Substack post's cached content, publication and save timestamps using its URL or local ID.
Retrieve full cached post details, timestamps (published_at and saved_at), and content by URL or local ID.
| Name | Required | Description | Default |
|---|---|---|---|
| url_or_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.3.1Output schema / properties / result / anyOfPrevious value: -[
- {
- "description": "Represents a Substack post record stored in SQLite.",
- "properties": {
- "audience": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "default": null
- },
- "author_name": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "default": null
- },
- "content_text": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "default": null
- },
- "created_at": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "default": null
- },
- "excerpt": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "default": null
- },
- "id": {
- "anyOf": [
- {
- "type": "integer"
- },
- {
- "type": "null"
- }
- ],
- "default": null
- },
- "image_url": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "default": null
- },
- "is_paywalled": {
- "default": 0,
- "type": "integer"
- },
- "is_saved": {
- "default": 1,
- "type": "integer"
- },
- "publication_name": {
- "type": "string"
- },
- "publication_url": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "default": null
- },
- "published_at": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "default": null
- },
- "reading_time_minutes": {
- "anyOf": [
- {
- "type": "integer"
- },
- {
- "type": "null"
- }
- ],
- "default": null
- },
- "saved_at": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "default": null
- },
- "substack_post_id": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "default": null
- },
- "title": {
- "type": "string"
- },
- "unsaved_at": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "default": null
- },
- "updated_at": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "default": null
- },
- "url": {
- "type": "string"
- },
- "word_count": {
- "anyOf": [
- {
- "type": "integer"
- },
- {
- "type": "null"
- }
- ],
- "default": null
- }
- },
- "required": [
- "url",
- "title",
- "publication_name"
- ],
- "type": "object"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "description": "Represents a Substack post record stored in SQLite.",
+ "properties": {
+ "audience": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+ },
+ "author_name": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+ },
+ "content_text": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+ },
+ "created_at": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+ },
+ "excerpt": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+ },
+ "id": {
+ "anyOf": [
+ {
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+ },
+ "image_url": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+ },
+ "is_fully_read": {
+ "readOnly": true,
+ "type": "boolean"
+ },
+ "is_paywalled": {
+ "default": 0,
+ "type": "integer"
+ },
+ "is_saved": {
+ "default": 1,
+ "type": "integer"
+ },
+ "is_viewed": {
+ "default": 0,
+ "type": "integer"
+ },
+ "max_read_progress": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+ },
+ "minutes_remaining": {
+ "anyOf": [
+ {
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "readOnly": true
+ },
+ "publication_name": {
+ "type": "string"
+ },
+ "publication_url": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+ },
+ "published_at": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+ },
+ "read_progress": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+ },
+ "reading_time_minutes": {
+ "anyOf": [
+ {
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+ },
+ "saved_at": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+ },
+ "substack_post_id": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+ },
+ "title": {
+ "type": "string"
+ },
+ "unsaved_at": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+ },
+ "updated_at": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+ },
+ "url": {
+ "type": "string"
+ },
+ "word_count": {
+ "anyOf": [
+ {
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+ }
+ },
+ "required": [
+ "url",
+ "title",
+ "publication_name",
+ "is_fully_read",
+ "minutes_remaining"
+ ],
+ "type": "object"
+ },
+ {
+ "type": "null"
+ }
+]v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations available, the description carries the burden of behavioral disclosure and does convey that this is a read-only retrieval of cached data, not a mutation. However, it omits useful behavioral context such as what happens if the post is not found, whether the cache can be stale, or whether any fetch/refresh is triggered.
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 entire description is a single, well-ordered sentence that front-loads the action and then packs only useful qualifiers: full, cached, timestamps, content, URL/local ID. There is no filler, redundancy, or unnecessary elaboration.
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 simple one-parameter getter with an output schema already present, this description provides the essential information: what resource is being retrieved, what identifying data is accepted, and what major fields the result includes. It could be more complete by explaining how it relates to the sibling tools, but for this low-complexity tool the essentials are not missing.
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 schema provides only an unannotated string property 'url_or_id' with zero description coverage. The tool description compensates by explicitly stating that either a URL or a local ID can be supplied, which is the essential semantic needed to populate the single required parameter. It does not specify edge-case formats, but the coverage for a one-parameter tool is adequate.
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 uses a concrete verb 'retrieve' and clearly identifies the resource: full cached post details, including timestamps and content. The clarification that lookup can be by URL or local ID makes the tool's job unambiguous and distinguishes it from sibling tools like list_saved_posts or get_post_content.
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 explicit guidance is provided about when to use this tool versus alternatives such as search_saved_posts, list_saved_posts, or get_post_content. The description implies a retrieval use case but does not state conditions, exclusions, or preferred scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/toniher/substack-saved-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server