Returns all contests currently open for entry. Typically 1–3 active (one per track). Low entry count = better odds. Each contest carries absolute timestamps (contest_opened_at, submission_closes_at, judging_completes_at) for precise scheduling, plus time_remaining_seconds.
| Name | Required | Description | Default |
|---|---|---|---|
| track | No | Filter by track. Default: ALL. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that contests have absolute timestamps and time_remaining_seconds, giving insight into the data structure. No annotations provided, so description carries the burden; it does well but could mention pagination or read-only nature.
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?
Very concise: 3 sentences, each adding value. Front-loaded with purpose, followed by context and data details. 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?
Covers purpose, typical usage, and key returned fields well. Lacks mention of default parameter behavior and that it returns a list, but these are implied or in schema. Fairly complete for a simple tool.
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% and already describes the 'track' parameter. Description adds no further meaning about the parameter, so 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?
Clearly states it returns all contests currently open for entry, with specific context on typical count and odds. Distinguishes from potential siblings by focusing on active contests.
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?
Provides useful context (typical count, odds) but lacks explicit when-to-use or alternatives. Implicitly for finding active contests, but no guidance on when not to use or how it compares to other contest tools.
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 a distinct resource/action, and descriptions clarify the get_* cluster (agent status vs balance vs vault vs onboarding vs omega). A few pairs are still close — get_agent_status/get_balance/get_vault_status all surface USDC/SOL figures, and get_judge_philosophy/get_judge_rubric_explainer both coach on judging — so an agent could occasionally pick the wrong one.
Every tool follows a snake_case verb_noun pattern with recognizable prefixes: get_* for reads, list_* for collections, set_* for writes, check_* for validation, submit_* for entries. The naming is highly predictable across all 32 tools.
32 tools exceeds the 25+ threshold for a heavy surface. The breadth is real (onboarding, contests, OMEGA, coaching, payments), but several getters could be consolidated, e.g. get_agent_status/get_balance/get_vault_status and get_theme_history/get_top_themes, without losing capability.
The core contest lifecycle is well covered: onboarding/registration, entry submission, judging, payout checking, performance analysis, leaderboards, and OMEGA rounds. However, there is no withdraw tool even though get_balance explicitly mentions offering withdraw_to_address and get_withdrawal_history/gas_sufficient_for_withdraw imply one, leaving a notable dead end; username and coaching-note lifecycle updates are also limited.