Get recent transaction signatures for an address. Returns up to 20 most recent.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max signatures to return (default 20, max 1000) | |
| address | Yes | Account address (base58) |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description claims 'up to 20 most recent' but schema allows limit up to 1000, creating a direct contradiction. No mention of read-only behavior or other traits. With no annotations, description carries full burden but is misleading.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded, but second sentence is inaccurate regarding limit. Conciseness undermined by inaccuracy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Has output schema, so return values are covered, but description fails to accurately describe limit behavior (contradicts schema). No explanation of pagination or how to get more than 20 signatures. Incomplete for safe usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Both parameters have schema descriptions with 100% coverage. Description adds no new detail about parameters beyond schema, achieving baseline for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states verb 'Get', resource 'transaction signatures for an address', and scope 'recent, up to 20 most recent'. Distinct from sibling tools like solana_getTransaction which retrieves a single transaction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implied usage to retrieve signatures for an address, but no explicit guidance on when to use versus solana_getTransaction or other siblings. No when-not-to-use or alternative hints.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tool pairs overlap in function: aex402_quote vs aex402_buildSwap, search vs search_tokens vs discover_programs, describe_program vs reconstruct_abi, and mcp_linq vs agent_delegate. Descriptions attempt to differentiate, but boundaries are fuzzy and an agent could easily select the wrong one when uncertain.
Naming is inconsistent: some tools use camelCase (aex402_buildSwap) while most use snake_case, verbs vary widely (build, get, list, quote, search, describe, discover, launch, delegate, chat), and there is no uniform verb_noun pattern. This makes predicting tool names difficult.
32 tools is excessive for a single MCP server, exceeding the 25+ threshold. While the scope is broad (AMM, bridge, AI, RPC, discovery, launchpad), many tools could be consolidated (e.g., search tools) or are too fine-grained (multiple solana_get* tools).
Core workflows are well covered: AMM (quote/build/get/list), bridge (quote/status), AI (chat/delegate/linq), Solana and EVM RPCs, search/discovery plus health check, launchpad, and payment help. Minor gaps include no direct bridge history or AMM execution, but these are intentional in a non-custodial design.
