Adversarial red-team of a trading claim/backtest: small-n, CI, tail-driven expectancy, asymmetric window, circularity, unaccounted cost. Returns flags + verdict. K1 verification service.
| Name | Required | Description | Default |
|---|---|---|---|
| n | No | ||
| claim | No | ||
| sample | No | ||
| win_rate | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden and does it reasonably well: it discloses the analytical nature of the tool, the specific verification dimensions considered, and the output shape ('flags + verdict'). It does not detail side effects, auth, or exact flag semantics, but the tool appears to be a read-oriented verification service, and the disclosure is meaningful beyond the tool name.
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 dense sentence with the core action front-loaded, followed by a compact checklist of quality dimensions and the return summary. Every phrase adds useful information, with no filler or repeated schema content.
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 4-parameter tool with no schema descriptions and no output schema, the description covers the tool's purpose and general output but leaves important invocation details unclear: how sample and win_rate are used, whether inputs are optional, and what the verdict/flags values look like. It is adequate but not 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?
Schema description coverage is 0%, so the description must compensate for the 4 undocumented parameters. It only implicitly hints at 'n' via 'small-n' and mentions 'claim', but 'sample' and 'win_rate' are never explained, and no parameter mapping or usage examples are provided. This is a clear gap for an agent trying to construct a valid invocation.
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 phrase, 'Adversarial red-team of a trading claim/backtest', and names the exact resource being acted on. It adds a concrete list of verification dimensions and reports that it returns flags plus a verdict, clearly distinguishing it from the crypto/swap/mint-focused 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 gives clear context for when the tool is appropriate: when a trading claim or backtest needs adversarial verification/red-teaming. It does not explicitly name alternatives or exclusion conditions, but the purpose is specific enough that an agent can infer the intended use.
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 target clearly distinct actions (build, check, score, verify, track), and the detailed descriptions separate chains and purposes. The main ambiguity is between check_robinhood and check_robinhood_honeypot, which both assess Robinhood Chain tokens but via different methods.
Most names follow a verb_noun pattern with a consistent 'check_' family for safety tools. Minor deviations like recent_events, guard_pricing, and track_record break the pattern but are still readable.
Ten tools is well within the ideal range and covers safety checks, signal intelligence, execution, pricing, and verification without feeling padded. Each tool has a distinct role in the guarded-trading workflow.
The surface covers the core non-custodial trading/intelligence loop: assess, score, copy, build, pay, and verify claims. Minor gaps exist around historical signal filtering or arbitrary-wallet deep dives, but they are workarounds rather than dead ends.