TronSave MCP Server

Extendable Delegates

tronsave_list_extendable_delegates

Read-onlyIdempotent

List extendable delegate candidates for a receiver and resourceType (ENERGY|BANDWIDTH). Optional suggestData scores an extend-and-buy scenario for planning purposes. Read-only; does NOT create orders or change on-chain state. Works without mcp-session-id; when a session is present, auth is forwarded so results can reflect the logged-in account where supported. NOTE: this is GraphQL market data for discovery only. To actually submit an extension, call the authenticated REST POST /v2/get-extendable-delegates with extendData (payload shape differs from this GraphQL response).

Input Schema

TableJSON Schema

Name	Required	Description
`receiver`	Yes	TRON base58 address (typically starts with `T`) that currently receives or will receive the delegated resource. This is the primary filter: the response describes delegates relevant to extending that account's delegation.
`requester`	No	Optional TRON base58 address of the viewing/requesting party. When an MCP session is active, the server may still derive identity from auth headers; use this when the API expects an explicit requester string distinct from the receiver.
`suggestData`	No	Optional nested scenario for extend-and-buy suggestion scoring. If omitted, the query returns delegate rows without that hypothetical. If provided, supply all four fields together; partial objects are invalid for typical GraphQL input shapes.
`resourceType`	Yes	Which resource market leg to query: `ENERGY` for contract execution headroom, `BANDWIDTH` for transaction bandwidth. Must match how you plan to extend or buy.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`extendableDelegates`	Yes	Null when the market has no payload or GraphQL returned no branch; check tool-level errors for hard failures.

TDQS

A4.9/5.0

Behavior5/5

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

Description confirms read-only and idempotent behavior, matching annotations. It adds context: GraphQL market data, session behavior, and that suggestData is for hypothetical scoring only. No contradictions and provides rich behavioral context beyond annotations.

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?

The description is somewhat long but every sentence serves a purpose. It front-loads the key action and then layers details logically. Minor redundancy could be trimmed, but overall efficient for the complexity.

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 moderate complexity (4 params, nested object, output schema exists), the description covers all aspects: purpose, parameters, behavior, session handling, and relationship to sibling tools. No gaps remain.

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?

With 100% schema coverage, the description still adds significant value: receiver typo? Actually explains address format and filter; requester clarifies when to use; suggestData details nested fields and warns against partial objects; resourceType clarifies use cases. All parameters are thoroughly explained beyond schema.

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 verb 'list', the resource 'extendable delegate candidates', and the key parameters (receiver, resourceType). It distinguishes itself from sibling tools by noting it is GraphQL market data for discovery only, not for order creation, and references the REST endpoint for actual submission.

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?

It explicitly states when to use ('Read-only; does NOT create orders or change on-chain state'), notes that it works without mcp-session-id and explains auth forwarding. It guides toward the REST endpoint for actual extensions, providing clear alternatives.

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

All TronSave MCP Server tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation4/5

Most tools have clearly distinct purposes, with some overlap between signature-based and internal API-based variants (e.g., create_order vs internal_order_create). Descriptions are thorough and help disambiguate. The minor overlap is justified by different authentication methods.

Naming Consistency5/5

Tool names follow a consistent 'tronsave_verb_noun' pattern with clear segmentation (e.g., get/list for retrieval, create/update/cancel for mutations). Internal tools use a consistent 'internal_' prefix. No mixing of conventions.

Tool Count4/5

29 tools is on the higher end but appropriate for a DeFi platform covering multiple resource types, order management, auto-settings, internal accounts, extensions, and authentication. A few tools could be merged (e.g., estimate variants) but overall scope justifies the count.

Completeness3/5

Major operations (CRUD for orders, auto-sell settings, internal account) are covered. Notable gaps include missing create/update tools for auto-buy rules (only delete exists) and limited history for signature-based orders (only internal order history available).

Resources

Need Help?