Footdigest: the live model card behind every prediction. Returns the backtested RPS versus a naive baseline, the out-of-sample size, the calibration table, the methodology, and an explicit list of what is not measured. Use it to audit any number the other tools return.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description discloses the returned components and the audit purpose. It could add details about data freshness or prerequisites, but the provided information is sufficient for a read-only tool.
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?
Two concise sentences: first introduces the tool, second lists contents and usage. No wasted words.
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 no output schema and no parameters, the description adequately covers what the tool does and returns. Could mention if data is static or refreshed, but overall 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?
No parameters in input schema (100% coverage). Description adds value by explaining the output, meeting the baseline for zero-parameter tools.
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 tool returns a 'live model card' with specific components (RPS vs baseline, out-of-sample size, calibration table, methodology, list of not measured). It distinguishes itself from sibling tools by focusing on auditing model predictions.
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?
Explicitly says 'Use it to audit any number the other tools return', providing a clear use case. No explicit exclusions, but the context of sibling tools makes the usage context clear.
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.
Each tool targets a distinct aspect of football competition analysis—brackets, match details, probabilities, standings, injuries, etc.—with no overlapping purposes that would confuse an agent.
Most tools follow a consistent 'get_' prefix with descriptive noun phrases, but 'simulate' deviates from the pattern, and 'get_head_to_head' uses hyphens. Overall, the naming is clear and predictable.
With 14 tools, the set feels well-scoped for a football competition analytics server. Each tool serves a clear purpose, covering predictions, match data, standings, and team status without unnecessary clutter.
The tool surface covers all major areas of competition analysis: schedules, standings, brackets, head-to-head, match details (including AI briefs), probabilities, model auditing, qualification scenarios, tournament odds, simulations, suspensions, and injuries. No obvious gaps for the intended domain.
