Read SocialFetch docs page
docs_readRead a documentation corpus page by its pathname from search results to retrieve API parameters, credits, and field details; use full mode to include examples and SDK snippets.
Instructions
Read a corpus page by docsPathname from docs_search. Defaults to mode=outline (compact field digest). Pass mode=full for Examples/SDK snippets. Accepts /docs/... and /product/... pathnames (including /product/ask-ai/field-crosswalk).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"docsPathname": "<docsPathname>",
"context": "<context>",
"llm_model": "<llm_model>"
},
"name": "docs_read"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | outline (default) = compact params/credits/field digest. full = complete page including Examples. | outline |
| context | Yes | Describe the user's underlying goal in one sentence, not the tool you are calling. | |
| llm_model | Yes | The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess. | |
| docsPathname | Yes | Corpus pathname from docs_search, e.g. /docs/api/v1/tiktok/videos/get or /product/ask-ai/field-crosswalk. Trailing .mdx accepted. | |
| conversation_id | No | Echo the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it. |