Skip to main content
Glama
trustxai

amazing-binance-mcp

by trustxai

binance_get_all_withdrawals

Read-onlyIdempotent

Fetch all crypto withdrawals from your Binance account since 2017, including fees, using resumable pagination to cover multi-year history for audits.

Instructions

Every crypto withdrawal since since — the 90-day cap walked for you.

Same walk as binance_get_all_deposits (89-day windows newest-first, offset paging by 1000 inside each, dedupe by Binance id), against GET /sapi/v1/capital/withdraw/history. Reading only — this server can never submit a withdrawal.

⚠️ Each call costs UID weight 18000 of the 180000/min per-account budget, and the endpoint separately allows only 10 requests per second. That is why max_calls defaults to 10 — one full minute of UID budget — instead of the 60 the deposit walk uses. A full 2017→today sweep needs ~35 windows, so expect to resume across several calls; the cursor makes that exact and gap-free.

since defaults to 2017-07-01, Binance's launch: no API reports an account's creation date (apiRestrictions.createTime is the API KEY's date).

When to Use:

  • "Show me every withdrawal I have ever made", including the fees they cost.

  • Auditing money going OUT, for tax or reconciliation.

When NOT to Use:

  • For one recent window — binance_get_withdraw_history is one call.

  • For deposits — use binance_get_all_deposits.

  • To MAKE a withdrawal — impossible by design.

Returns: Rows sorted newest-first with per-coin totals (count, summed amount, summed transactionFee). Markdown displays at most 50 rows; response_format="json" returns {count, truncated, no_progress, since, until, resume_before, calls_made, totals, items} with the full set. truncated is true exactly when the walk did not reach since; no_progress is true when it did not finish even the first window, and then resume_before is null on purpose — see Pagination.

Pagination: If the walk stops before since — which with max_calls=10 is the normal case for a multi-year sweep — it returns the rows it has PLUS resume_before, the boundary of the next UNFETCHED range. Call again with the same since and that resume_before; repeat until truncated is false. If not even the first window completed, resume_before is null and no_progress is true: raise max_calls and re-run the same range, since resuming at until would repeat the identical calls.

Examples: params = {} params = {"since": "2024-01-01", "coin": "BTC"} params = {"since": "2017-07-01", "resume_before": 1717200000000, "max_calls": 10}

Error Handling: An over-wide-window error is tolerated (the window is halved and retried). Auth (-2015), rate limits (429/418) and envelope failures stop the walk immediately and are reported alongside the rows already collected and the resume cursor.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
paramsYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A5/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false; the description adds substantial operational detail: UID weight 18,000 per call, 10 req/s limit, default max_calls=10 rationale, windowed walking with dedupe, resume_before cursor, no_progress/truncated flags, and error handling. It reinforces the read-only claim and never contradicts annotations.

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

Conciseness5/5

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

The description is lengthy but well-structured with clear section headings (rate limits, when to use, returns, pagination, examples, error handling). Every section serves a purpose for a complex windowed-walk tool, and the core purpose is front-loaded. No superfluous filler is present.

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?

The description covers semantics, rate limits, defaults, return shape, pagination protocol, examples, and error handling. An output schema exists, so restating return fields is unnecessary; nonetheless, the description explains the top-level JSON keys and truncation behavior. Nothing an agent needs to invoke and recover from a partial walk is missing.

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?

Although the schema itself documents each parameter, the description goes beyond by explaining the operational significance: why max_calls defaults to 10 based on the UID budget, how resume_before is meant to be reused, and what no_progress/truncated semantically mean. This adds meaningful guidance beyond the schema's property descriptions.

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 opens with 'Every crypto withdrawal since `since` — the 90-day cap walked for you', clearly stating the tool's function and scope. It explicitly contrasts itself with binance_get_withdraw_history and binance_get_all_deposits, so an agent can distinguish it from siblings even without reading schemas.

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?

Dedicated 'When to Use' and 'When NOT to Use' sections give concrete alternatives and conditions, such as using binance_get_withdraw_history for a single recent window and binance_get_all_deposits for deposits. It also states that making a withdrawal is impossible by design, leaving no ambiguity about misuse.

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

Deploy Server

Other Tools