Skip to main content
Glama
KhiipAI

Khiip

Official
by KhiipAI
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

refetch_capture

Refresh a specific dimension of an existing web capture—re-extract data, re-render markdown, update media status, or submit to Wayback—by providing the capture ID.

Instructions

Refetch one dimension of an existing capture.

Dimensions, per ADR-0010 commitment 6 + ADR-0009 §C2 replay (S42):

  • extraction (default): NETWORK re-fetch → new capture, old marked superseded (can observe a changed/deleted post).

  • re-extract: OFFLINE — re-derive the typed payload from the preserved source bytes with the current extractor (recovers under-extracted fields; survives source deletion). In place; same capture id.

  • re-render: OFFLINE — re-render the markdown body from the existing typed payload (apply an improved renderer / skin). In place.

  • media: re-walk MediaFetcherRegistry on existing payload; updates Media[].download_status in place; same capture id.

  • wayback: re-submit canonical URL to Wayback Save Page Now; updates archive_urls['wayback'] in place; same capture id.

Args: capture_id: The capture ULID to refetch. dimension: Which dimension to refetch (extraction | re-extract | re-render | media | wayback). Defaults to extraction.

Returns: Updated capture record on success; structured error dict on failure.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dimensionNoextraction
capture_idYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Tool Definition Quality

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Despite no annotations, the description thoroughly explains each dimension's behavior: extraction involves a network re-fetch and marking the old capture superseded; re-extract, re-render, media, and wayback all operate in-place. It also states the return value. No contradictions or hidden side effects noted.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with a one-line summary but includes technical references (ADR-0010, ADR-0009, S42) that may be unnecessary for an AI agent. Some sentences could be more concise without losing clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of multiple dimensions and no output schema, the description covers what each dimension does, the parameters, and the return type. It is complete and leaves no major gaps for agent understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Both parameters are well-documented: capture_id is described as 'The capture ULID to refetch' and dimension is explained with a list of allowed values and their defaults. The schema description coverage is 0%, so the description fully compensates.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Refetch one dimension of an existing capture.' It enumerates the five dimensions with detailed explanations, distinguishing the tool from siblings like get_capture or list_captures.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied through the dimension descriptions, but there is no explicit guidance on when to use this tool versus alternatives like get_capture (for reading) or capture_url (for initial capture). No when-not-to-use or exclusion criteria are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/KhiipAI/khiip'

If you have feedback or need assistance with the MCP directory API, please join our Discord server