get_defi_tvlReturn total value locked (USD) across the Flare DeFi ecosystem with a per-protocol breakdown (protocol name, TVL, token count). Source is on-chain reads valued at current prices. available=false / total null when the price-dependent TVL read is unavailable.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint annotation, the description discloses the data source ('on-chain reads valued at current prices') and the failure/edge-case behavior ('available=false / total null when the price-dependent TVL read is unavailable'). This is exactly the kind of behavioral context that helps an agent interpret unexpected responses.
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 succinct sentences. The first states the purpose and output fields; the second adds data source and an edge-case behavior. No filler or repetition of annotation data.
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 no-parameter, read-only tool, the description covers the output breakdown, units, data source, and unavailability behavior. Even without an output schema, an agent has enough to call this tool and interpret its result.
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?
The tool has zero parameters and the schema coverage is 100%, so parameter explanation is unnecessary. The description still adds value by previewing the result shape and the condition under which the total is null, giving the agent context beyond the empty schema.
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 opens with a specific verb and resource: 'Return total value locked (USD) across the Flare DeFi ecosystem with a per-protocol breakdown.' It names the exact output fields (protocol name, TVL, token count) and distinguishes this from price or validator-related sibling tools.
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 makes clear this is the tool for DeFi TVL inquiries by stating the exact metric and scope. It does not explicitly name alternatives or exclusions, but no sibling tool covers the same deliverable, so the usage context is clear.
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.
Most tools are cleanly separated by resource and action: list/compare/detail for validators and FTSO providers, network_* for distinct metrics, and get_my_* for wallet concerns. A couple of pairs could be confused (get_my_claimable vs get_my_rewards_history, and the network_* trio), but the descriptions provide enough boundary detail to pick correctly.
Naming is highly consistent: all tools use snake_case with a leading verb (get_, list_, compare_, simulate_, verify_). The pattern is predictable, so an agent can infer the shape of an operation before reading its description.
At 27 tools, the surface exceeds the 25-tool threshold and feels heavy, especially with five get_my_* personal tools, five agent-oriented tools, and three network_* tools. The broad scope explains some of the count, but many of these could be consolidated or split across separate servers.
The read-only analytics surface is quite comprehensive: validators, FTSO providers, network economics, chain activity, DeFi, FAssets, prices, feeds, personal balances, delegations, and agent status are all covered. Explicit gaps remain, such as FLR-side claimables, full tax record assembly, and a complete per-epoch rewards timeline, but these are clearly flagged as follow-on phases rather than dead ends.