Over-by-over win-probability timeline (the broadcast 'worm') for a full T20 chase. Media/broadcast-grade. Pay per call via x402.
| Name | Required | Description | Default |
|---|---|---|---|
| events | Yes | Per-over states [{balls_bowled, wickets, cum_runs, target}]. | |
| target | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must bear full burden. It discloses that the tool is paid and broadcast-quality, but fails to specify output format (e.g., JSON structure), data freshness (real-time vs. historical), or any side effects. The phrase 'the broadcast worm' hints at a common visualization but does not clarify what the tool returns.
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 lines, front-loaded with the core purpose and key differentiators (broadcast-grade, pay-per-call). Every sentence adds value without redundant information. One minor point: the second sentence could be merged for smoother flow, but it remains clear and efficient.
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?
With no output schema and only 2 parameters, the description is insufficiently complete. It explains the input format (events per over) but omits the output format (e.g., array of probabilities, percentage values). Users cannot fully understand what the tool returns without additional inference.
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 50% with 'target' having an empty description. The tool description adds context by defining 'events' as per-over states and implying 'target' is the chase target. However, it does not fully compensate for the missing parameter documentation; more detail on the expected format for 'target' would improve utility.
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 it provides an 'over-by-over win-probability timeline' for a 'full T20 chase', using the familiar 'broadcast worm' analogy. This specific verb+resource combination distinguishes it from sibling tools like hsh-cricket-chase-winprob or hsh-cricket-chase-difficulty, which infer aggregate or pre-chase probabilities.
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?
The description implies usage for broadcast/media purposes ('Media/broadcast-grade') and mentions payment ('Pay per call via x402'), but does not explicitly state when to use this tool over alternatives such as hsh-cricket-chase-winprob or hsh-cricket-first-winprob. No when-not-to-use conditions or alternative tool names 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 purposes, but some closely related tools (e.g., hsh-b2b-*, hsh-esg-* variants) could cause confusion. Descriptions help differentiate, but an agent might still misselect similar products.
Naming convention is mixed: some tools use hyphens (hsh-b2b-contact), others use underscores (hsh_broker_data_request). While mostly readable, the inconsistency could be confusing for agents expecting a uniform pattern.
32 tools is on the high side for a single server, but given its purpose as a data marketplace, the large number reflects a wide catalog. However, it may be overwhelming for agents to navigate.
Covers many data domains but has obvious gaps (e.g., weather, social media). The inclusion of custom data request tools (hsh_describe_data_need, hsh_broker_data_request) mitigates these gaps, allowing agents to request missing data.
