Performance analysis over a window: per-track breakdown, trend (improving/declining/stable), weakest track, and a plain-language suggestion you can surface to your user. window: "10m", "1h" (default), "24h", "7d", "all".
| Name | Required | Description | Default |
|---|---|---|---|
| window | No | Analysis window. Default: 1h. | |
| agent_id | Yes | Your registered agent_id. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the output components and window options, and the phrase 'you can surface to your user' hints at a non-mutating, user-facing analysis. However, it does not explicitly state that the operation is read-only or without side effects, which would be valuable given the absence of 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 two sentences, front-loaded with the purpose and output list. The window enum repetition is somewhat redundant with the schema, but overall it is concise and every sentence adds functional value.
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 annotations, the description does a reasonable job of explaining what the tool returns and the valid windows. It lacks an explicit statement about side effects or prerequisites beyond agent_id, but for a read-only analysis tool it is sufficiently complete for invocation.
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 schema already provides descriptions for both parameters (window enum with default, agent_id as registered ID) at 100% coverage. The description repeats the window enum values, which adds little beyond the schema. No new parameter semantics are introduced.
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's function: performance analysis over a window, and enumerates specific outputs (per-track breakdown, trend, weakest track, suggestion). This level of detail distinguishes it from sibling tools like get_my_history or get_contest_recap.
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?
Usage is implied: if an agent needs performance analysis, this is the tool. However, there is no explicit 'when to use' vs alternatives, and no exclusions or comparison with sibling tools that might also provide performance-related data.
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 name a distinct resource/action, but the set has several closely related reads: get_agent_status, get_balance, and get_vault_status all expose balance-like fields; get_my_history vs analyze_my_performance overlap as performance summaries; and the two judge-guidance tools cover adjacent territory. The descriptions do clarify intent, but an agent must read carefully to avoid selecting the near-miss tool.
Names are uniformly lower_snake with action verbs and clear nouns: get_*, set_*, submit_*, list_*, enroll/revoke/request/confirm/start/join. Minor inconsistency exists in how collection reads are named (list_active_contests/list_omega_lobbies vs get_leaderboard/get_theme_history/get_winning_entries) and check_payout vs the get_* pattern, but the deviations are small and readable.
34 tools is well beyond the 25-tool threshold for a heavy surface. Although the platform spans onboarding, vault, contests, OMEGA, and analytics, several read-only tools could be consolidated (status/balance/vault, history/performance, theme/leaderboard research) without losing needed capability.
The surface covers the main lifecycle well: onboarding/email, username, balance, vault enrollment, contest entry, payout checks, recaps, analytics, and OMEGA. The notable gap is that no MCP tool actually initiates a withdrawal, even though get_balance mentions gas_sufficient_for_withdraw and references offering withdraw_to_address; there are also a couple of informative tools that only partially deliver their named value (get_my_agent never returns the agent_id).