get_scoresLive + recent final scores. Costs 2 requests per call.
| Name | Required | Description | Default |
|---|---|---|---|
| days_from | No | 1-3 days from now (default 1) | |
| sport_key | Yes |
| 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?
The annotations already indicate this is a safe, read-only, idempotent operation, so the description's main contribution is the disclosure that each call costs 2 requests. This is a meaningful operational trait not captured in the annotations. The description adds this valuable context without contradicting the 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 short sentences that efficiently convey the core purpose and a key operational constraint. There is absolutely no filler or redundancy; 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 the tool's simplicity, the presence of an output schema, and comprehensive annotations, the description covers the basic purpose and cost. However, it lacks usage guidance relative to sibling tools and leaves the sport_key parameter undocumented, creating a clear gap. It is minimally viable 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?
The description does not clarify any parameter semantics. The schema describes 'days_from' adequately, but 'sport_key' has no description and is required. The description does not compensate for this gap, leaving the agent to infer what values are valid for sport_key. With only 50% schema description coverage, the description should have provided additional parameter context but does not.
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 identifies the resource as scores, specifically 'Live + recent final scores', which distinguishes it from sibling tools like get_odds or get_events. While it lacks an explicit verb, the title 'Get Scores' and context make the purpose unambiguous. It does not explicitly differentiate from siblings beyond the resource type, but the scope is clear.
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?
There is no guidance on when to use this tool versus alternatives such as get_odds or get_events. The only additional note is the cost ('Costs 2 requests per call'), which is an operational consideration but does not help the agent choose between tools. No exclusions or conditional usage are provided.
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.