searchEvmTokensBirdeyeSearch for EVM tokens on Birdeye. Supports Ethereum, BSC, Polygon, Base, and Robinhood Chain.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query | |
| chainId | Yes | Chain ID to search tokens on |
Changes observed during successful MCP inspections.
Input schema / properties / chainId / enumPrevious value: -[
- 1,
- 56,
- 137,
- 8453
-]New value: +[
+ 1,
+ 56,
+ 137,
+ 8453,
+ 4663
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish the operation as safe (readOnlyHint, idempotentHint, notStrong destructive), so the baseline is lowered. The description adds helpful context by naming the supported chains and stating the EVM scope, which goes beyond the schema. It does not address optional details like rate limits or pagination, but these are not critical given the annotation coverage.
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?
No more than two sentences. The main action is placed immediately, and the chain list is concise and organized. There is no repetition of schema data and no redundant wording.
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 simple two-parameter search tool, the description is almost complete: it mentions the resource, the supported chains, and implies the output nature (token matches). It does not describe the output structure, but the various schema and read-only annotations do the position and cover the missing safety context. Minor gaps like query query format still contribute no risk of mis-invocation.
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 schema covers all parameters with descriptions, so the baseline is healthy. The description adds the chain family listing, giving numeric enum values a readable and semantic mapping to Ethereum, BSC, Polygon, Base, and Robinhood Chain. It does not specify what the query should contain (name, symbol, or contract), which holds it back from a 5.
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 names a specific action ('Search for EVM tokens') and the resource ('on Birdeye'), then enumerates the supported chains, giving the agent a crisp object of work. It differentiates from simpler search tools by explicitly bounding the tool to EVM chains and the Birdeye service.
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 statement implies usage: for searching EVM tokens by query on Birdeye across selected chains. However, it gives no explicit when-to-use guidance or distinction from closely related siblings like birdeyeTrendingTokens or searchCryptoByName, so the agent must infer when to choose this over another option.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.