Red-card reaction profile (market-adjusted vs CHZ). Rare and high-impact: returns abnormal return at +15/+30/+60m with honest wide confidence intervals and sample size; flags cells with n<15. Descriptive history, not advice.
| Name | Required | Description | Default |
|---|---|---|---|
| event_side | No | 'against' = token team's player sent off; 'for' = opponent sent off. | |
| minute_bucket | No | Optional match-minute bucket (e.g. '76-90' for late reds). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full transparency burden. It discloses statistical caveats ('honest wide confidence intervals and sample size', 'flags cells with n<15') and adds a disclaimer ('Descriptive history, not advice'). It does not explicitly state read-only or potential side effects, but given the analytical nature, the disclosure is strong.
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 two sentences with no filler. First sentence states purpose and key metrics. Second sentence adds statistical details and disclaimer. Every sentence earns its place.
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 the tool returns a statistical profile with no output schema, the description adequately conveys the output (abnormal returns at specified intervals, confidence intervals, sample size, and low-n flags). It covers key behavioral aspects but could be more explicit about the output structure (e.g., table vs. single value).
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 coverage is 100% with descriptions for both parameters (event_side and minute_bucket). The tool description mentions 'late game' which aligns with minute_bucket options but does not add additional semantic meaning beyond what the schema already provides. Baseline score of 3 is appropriate.
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 it returns a 'Red-card reaction profile' with specific metrics (abnormal return at +15/+30/+60m). It distinguishes itself from sibling tools like 'tokenintel_event_reaction_profile' by focusing specifically on red card events, using the phrase 'Rare and high-impact' to highlight uniqueness.
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 implies usage for red card events and notes it is 'descriptive history, not advice,' but does not explicitly state when to use this tool over alternatives such as tokenintel_event_reaction_profile or provide conditions where it should not be used.
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.
Every tool targets a distinct aspect of fan token intelligence (e.g., briefing, DEX depth, whale flows, event reactions). Detailed descriptions and usage notes (e.g., 'USE THIS for ...') clearly differentiate overlapping areas like token_context vs briefing.
All tools follow a consistent 'tokenintel_<descriptive_name>' snake_case pattern. The prefix is uniform, and names like 'tokenintel_goal_direction_asymmetry' or 'tokenintel_dex_liquidity' are predictable and clear.
22 tools is on the higher side but justifiable given the broad scope (market, sports, DEX, social, whale flows, meta-tools). The server covers many complementary functions without feeling bloated, though a few tools could potentially be merged.
The tool set covers the full lifecycle of fan token intelligence: overview (briefing), deep dive (token_context), prices, DEX analysis, whale flows, sports event reactions, social sentiment, health metrics, capital rotation, macro context, and even meta-tools (discover, describe, invoke). No obvious gaps for the stated purpose.