token_boosts_topMost-boosted tokens, optionally filtered to a chain / token.
| Name | Required | Description | Default |
|---|---|---|---|
| chain | No | ||
| token | No | Token address (chain required if passed) |
| Name | Required | Description | Default |
|---|---|---|---|
| boosts | No | Top boosted tokens | |
| schemaVersion | No | API schema version |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false, providing a strong safety profile. The description adds the behavior of filtering by chain/token, but does not detail data freshness, pagination, or ordering. With annotations covering core traits, this is adequate.
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?
One sentence, no waste, front-loaded with the core purpose. The examples in the input schema supplement the description without redundancy.
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?
The tool is simple with two optional parameters. The output schema exists, so return format is covered. The description and examples together provide sufficient context for an agent to use the tool correctly. No obvious gaps.
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 description coverage is 50% (token has description, chain does not). The overall description states both parameters act as optional filters, partially compensating for the missing schema description for 'chain'. The token parameter's description in the schema adds clarity about dependency on chain. This is adequate but not exceptional.
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?
Description clearly states the tool returns 'most-boosted tokens' with optional filtering by chain or token. The verb 'top' and resource 'tokens' are specific, and the mention of optional filtering distinguishes it from sibling tools like 'latest_boosted_tokens'.
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?
No explicit guidance on when to use this tool versus alternatives like 'latest_boosted_tokens' or 'latest_token_profiles'. There is no mention of use cases, prerequisites, or exclusions.
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 clusters overlap heavily: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all serve question-answering/research, and the six polymarket_* tools cover closely related prediction-market analysis. Long descriptions help differentiate them, but an agent could easily pick the wrong near-duplicate.
All names are snake_case and readable, but there is no consistent verb_noun pattern: some are verbs (search_pairs, validate_claim), some noun phrases (latest_token_profiles, entity_profile), and some prefixes (pipeworx_*, polymarket_*) cover only subsets. The naming is understandable but stylistically mixed.
37 tools is far too many for a server labeled Dexscreener, especially since the majority of tools have nothing to do with DEX data. Even if this is intended as an all-in-one data/research server, the count exceeds what the apparent scope justifies and many tools feel bolted on.
For the DEX Screener domain, the core surface is covered: pair lookup, token lookup, search, latest profiles, and boosts. The broader Pipeworx/prediction-market side also has strong coverage with memory, subscriptions, entity resolution, and research tools. Minor gaps exist — some tools feel redundant or exploratory — but there are no critical dead-end workflows.