PerfectVector

Get SVG

get_svg

Read-onlyIdempotent

Show a delivered SVG again for free, or list the recent conversions.

With a conversion_id: a fresh 24-hour download link, the facts and, for a small SVG, its text. For a larger SVG's text, call with offset=0, then each next_offset with the first reply's sha256, and join the parts. A conversion that isn't delivered yet returns its status only. With no conversion_id: the account's 10 most recent conversions with their IDs. Never converts or charges.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_svg"
  }
}

Input Schema

Name	Required	Description	Default
`offset`	No
`conversion_id`	No
`expected_sha256`	No

Output Schema

Name	Required	Description
`code`	No	Set when the call could not proceed.
`offset`	No
`recent`	No
`sha256`	No
`status`	No
`message`	Yes	The reply's text without its IDs and SVG text, for hosts that show only this.
`file_name`	No
`svg_bytes`	No
`svg_inline`	No
`next_action`	Yes	What to do next; guidance, never spending permission.
`next_offset`	No
`request_key`	No
`download_url`	No
`conversion_id`	No
`credits_charged`	No	Credits charged by this call only.
`total_characters`	No
`credits_available`	No	The balance afterwards.
`download_expires_at`	No
`retry_after_seconds`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 29, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already cover read-only/idempotent/non-destructive, but the description adds real operational detail: the download link expires in 24 hours, undelivered conversions return status only, free re-download versus paid conversion, and the sha256-chained paging protocol. These are behaviors no annotation or schema field conveys.

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

Conciseness4/5

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

Front-loaded with the two modes, then mode-specific detail in short paragraphs; every sentence is functional. A little density in the paging sentence ('the first reply's sha256, and join the parts') costs a small amount of clarity but no padding.

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

Completeness4/5

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

With an output schema present, the description needn't enumerate return fields, and it still sketches what comes back per mode (link, facts, text chunks, status, ID list). It omits error behavior for an unknown/expired conversion_id and the size ceiling implied by the 2097152 offset maximum.

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

Parameters4/5

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

Schema coverage is 0%, so the description has to carry the parameters, and it does for all three: conversion_id selects re-fetch vs. listing, offset starts the text paging at 0, and expected_sha256 must come from the first reply and be passed on each next_offset call. It stops short of stating units for offset (bytes/characters) or that offset is nullable/ignored without an ID.

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?

Opens with a concrete verb+resource pair and a dual-mode scope: re-fetch a delivered SVG ('free') or list recent conversions. The 'Never converts or charges' clause cleanly separates it from convert_to_svg, so an agent can pick the right sibling without opening either schema.

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

Usage Guidelines5/5

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

Explicitly branches on the presence of conversion_id: with an ID you get a download link and facts, without one you get the 10 most recent conversions. It also gives the exact call sequence for paging through a large SVG's text and states the tool never spends credits, which is the key reason to prefer it over conversion siblings.

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

All PerfectVector tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?