Skip to main content
Glama

Loyal Spark Holder

Prepare Loyalty Token Transfer

prepare_loyalty_token_transfer

Build B20/ERC-20 transfer calldata for the holder wallet to send loyalty tokens to any address (submit tx locally).

Input Schema

NameRequiredDescriptionDefault
toNoRecipient wallet address.
amountYesWhole-token amount to transfer.
to_addressNoAlias for to (same as REST to_address).
token_addressYesLoyalty program token contract.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior3/5

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

The annotations declare a non-read-only, non-destructive, non-idempotent operation, and the description usefully clarifies that the tool itself does not submit anything — the write happens locally after it returns. It adds no information about authorization requirements, whether token_address must be a program the holder actually belongs to, or whether the build is deterministic across calls (relevant given idempotentHint=false). Given annotations already cover the safety profile, this is a modest but real contribution.

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?

A single sentence, front-loaded with the core action, with no filler. The closing parenthetical carries real meaning rather than padding. Slightly dense with 'B20/ERC-20' jargon that a non-chain-native agent may need to interpret.

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?

For a four-parameter preparation tool with full schema coverage and no output schema, the description covers the essentials: what is built, for whom, and that submission is the caller's job. The remaining gap is the return shape — an agent is not told whether it receives raw calldata hex, a full transaction object, chain ID, or nonce — which matters more precisely because no output schema exists. That is a real but bounded omission for a tool of this simplicity.

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

Parameters3/5

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

Schema description coverage is 100%, so all four parameters (to, to_address, amount, token_address) are already documented in the schema, including the alias relationship and the whole-token unit. The description adds no further parameter guidance, such as whether B20 differs from ERC-20 in required fields or how the alias conflict is resolved. Baseline 3 applies.

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

Purpose4/5

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

The description names a specific verb and artifact: 'Build ... transfer calldata' for sending loyalty tokens from the holder wallet to any address. That is clearly not a read or a submission, and 'B20/ERC-20' scopes the token standard. It stops short of naming a sibling (e.g. prepare_reward_redemption) as the contrasting case, so differentiation is inferential rather than explicit.

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?

The parenthetical '(submit tx locally)' conveys the key workflow fact that this tool only prepares data and the agent must broadcast the transaction itself. However, there is no statement of when to pick this over prepare_reward_redemption or other preparation tools, and no prerequisites (holder authorization, chain/network assumption) are given. Usage is implied rather than stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources