token_priceExperimental (outside the core SEC path; not covered by the published accuracy eval, may change or be withdrawn): DEX-aggregated price, FDV, market cap and 24h volume for a token contract. Cached 60s; not an oracle. Costs $0.01 per call.
| Name | Required | Description | Default |
|---|---|---|---|
| chain | No | base or ethereum. Default base. | |
| token | Yes | Token contract address. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint, which cover safety and open-world nature. The description adds valuable behavioral context beyond that: it is experimental, may change, cached for 60s, not an oracle, and costs $0.01 per call. This gives the agent important expectations about reliability and cost, which annotations do not convey. It does not contradict annotations.
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 a single, well-structured sentence that front-loads the critical caveats (experimental, may change) before listing the data provided. Every phrase earns its place: the warning, the metrics, the caching, the oracle disclaimer, and the cost. No fluff or redundancy; it is concise yet information-dense.
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?
Given there is no output schema, the description compensates by listing the key returned metrics (price, FDV, market cap, 24h volume), giving the agent a clear expectation of what to expect. It also covers practical aspects: caching, cost, and reliability (not an oracle). However, it does not specify units, formatting, or whether the response is a single object or includes additional fields. Still, for a read-only tool with strong annotations, it is fairly complete.
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 input schema covers 100% of parameters, with chain and token each described. The description does not add parameter-specific semantics beyond what the schema provides, but it does clarify the kind of data (DEX-aggregated metrics) that the tool returns, which indirectly informs parameter meaning. Since the schema already documents both parameters, a baseline score of 3 is appropriate; the description adds no extra parameter details.
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 states the function: providing DEX-aggregated price, FDV, market cap, and 24h volume for a token contract. It names the specific resource (token contract) and the data returned. While it does not explicitly contrast with siblings like token_report or who_holds, its focus on these specific metrics is distinct enough. The purpose is clear and specific, not a tautology.
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 provides important context for usage: it warns the tool is experimental, outside the core SEC path, not covered by accuracy eval, and may change or be withdrawn. It also notes caching and that it is not an oracle, implying caution for critical decisions. However, it does not explicitly say when to use this tool versus alternatives, nor give conditions for when not to use it. The guidance is implicit rather than explicit.
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 have clearly written descriptions, but several pairs overlap semantically: token_price/token_report, latest_filings/recent_filings, and institutional_holdings/who_holds/activist_stakes all require careful reading to pick the right one. The overlap is not severe enough for a 2, but it is still more than the occasional confusion.
Names are consistently snake_case and mostly descriptive, but the set does not follow one naming convention. It mixes noun phrases (crop_data, token_report, insider_trades) with verb phrases (lookup_company, compare_filings, verify_financial_claim), and pairs like latest_filings/recent_filings create avoidable confusion.
31 tools is too many for what is nominally an SEC Filings server, and the scope sprawls into unrelated domains such as EVM gas, tokens, prediction markets, crop data, and x402 auditing. The count does not feel earned by a coherent workflow; it feels like an uncurated bundle of endpoints.
The SEC filing workflow is reasonably covered: company lookup, search, latest/recent filings, section extraction, 8-K events, comparisons, ownership filings, and XBRL financial checks are all present. However, there is no full-filing retrieval endpoint, no deep company financial history beyond a single concept, and many non-SEC subdomains are only one-off data points, so the overall surface is still incomplete.