protocol_profileDeFi protocol analytics: TVL, yield pools, on-chain activity, health signals. Supports Raydium, Orca, marginfi, Drift, Jupiter, Kamino, Marinade, Jito, and more.
| Name | Required | Description | Default |
|---|---|---|---|
| protocol | Yes | Protocol slug (e.g. "raydium", "orca") or Solana program ID | |
| include_yields | No | Include yield pool data |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It enumerates data categories but does not state whether the operation is read-only, describe return format, pagination, rate limits, or handling of unsupported protocols. This leaves significant behavioral ambiguity for an analytics tool.
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?
The description is exceptionally concise: two sentences that front-load the core purpose and data categories, followed by supported protocols. Every word contributes value, with no repetition or filler.
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?
For a two-parameter tool without an output schema, the description provides a reasonable overview of the data scope. However, it lacks details on return shape, error cases, or any additional behavior, and with no annotations, the agent has limited context for invoking the tool in complex workflows.
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?
Schema documentation already covers both parameters thoroughly (protocol slug or Solana program ID, include_yields boolean with default). The description adds a broader list of supported protocol examples ('Raydium, Orca, marginfi...'), which is helpful but does not alter the baseline established by 100% schema description 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?
The description clearly identifies the tool as providing DeFi protocol analytics with specific data types (TVL, yield pools, on-chain activity, health signals) and a list of supported protocols. This makes the purpose clear and distinguishes it from sibling tools focused on tokens or wallets, though it lacks a direct action verb.
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?
The description does not provide explicit guidance on when to use this tool versus alternatives. It lists supported protocols, which implies a target use case, but there is no mention of when not to use it or how it compares to sibling analytics tools like compare_tokens or token_trend.
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 tools cluster around the same action: trending/discovery tools like feed_latest, trending_signals, runner_scan, trenches_scan, smart_money_trenches, attention_momentum, and consensus_signal heavily overlap, and perps_basis_signal, perps_cross_venue_funding, and perps_venue_comparison all cover similar venue/funding comparisons. An agent can distinguish them only by reading fine print, increasing misselection risk.
Most tools follow readable snake_case with strong domain prefixes (perps_*, stonk_*, smart_money_*, hyperliquid_*) and clear verb_noun actions for core operations like enrich_token and compare_wallets. Minor outliers like query, feed_latest, attention_momentum, and new_tokens break the pattern but remain predictable.
41 tools is well over the 25-tool threshold for a coherent agent surface. The set fragments into many micro-specialties—five stonk tools, six perps tools, and several overlapping memecoin scanners—that could be consolidated into broader composite tools without losing capability.
For a Solana token/wallet/perps intelligence platform, the surface is exceptionally broad: discovery, enrichment, due diligence, exit signals, wallet history, transaction parsing, protocol profiles, perps, stonk, and composite querying are all covered. Missing pieces are minor, such as general holder lists or raw transaction history, and can be worked around with existing tools.