get_eventsUpcoming + live events for a league (without odds — useful to discover event IDs).
| Name | Required | Description | Default |
|---|---|---|---|
| event_ids | No | ||
| sport_key | Yes | ||
| date_format | No |
| Name | Required | Description | Default |
|---|---|---|---|
| count | Yes | Number of items returned. | |
| items | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate safe, read-only, idempotent behavior. Description adds context: returns upcoming+live events, no odds, and purpose for ID discovery. No contradictions.
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?
Single sentence, front-loaded with key info, no filler. Every word 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 existence of output schema, description need not explain return values. However, with 3 undocumented parameters and no schema description, some gaps remain. Adequate for a simple tool but not fully 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 coverage is 0%, so description must compensate but provides no parameter details. Purpose is clear but does not explain sport_key, event_ids, or date_format formats. Output schema exists but not referenced.
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?
Description clearly specifies verb (get), resource (events for a league), and distinguishes from siblings like get_event_odds by stating 'without odds'. It also explains the utility (discover event IDs).
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?
Description implicitly advises when to use (when event IDs needed without odds) by contrasting with odds-including tool. However, it does not explicitly state when not to use or name alternatives like get_event_odds.
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 have distinct scopes, and the long cross-referencing descriptions help a lot. However, ask_pipeworx_beta is currently an exact duplicate of ask_pipeworx by the server's own description, and the polymarket_* family plus ask_pipeworx/ask_pipeworx_grounded/deep_research have overlapping boundaries that could mislead an agent.
The vast majority follow a clear verb_noun snake_case pattern like get_odds, list_sports, resolve_entity, and subscribe. A few exceptions such as odds_api_quota, pipeworx_feedback, polymarket_arbitrage, and recall break the pattern slightly, but the overall convention is predictable.
37 tools is well past the 25+ threshold and feels bloated for a server named 'Odds Api'. Many tools are meta-platform utilities — memory, feedback, trending, dependency scanning, llms.txt generation — that have no obvious connection to an odds API and make the surface hard to navigate.
The odds domain is well covered: list_sports, get_events, get_odds, get_event_odds, get_scores, quota tracking, and subscriptions form a coherent read/monitor workflow. Minor gaps exist — no historical odds or a single-event detail endpoint — but agents can complete core odds research and monitoring tasks without dead ends.