puntersedge

Best price per runner

best_odds

Read-onlyIdempotent

The best available win and place price for every runner in upcoming races and which bookmaker has it, after PuntersEdge's guards (books pricing under 100%, quotes read before a scratching and placeholder prices never win). Also how many books quote each runner, the best-vs-worst spread, and each race's market percentage on best prices. Costs 3 credits. Every plan.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "best_odds"
  }
}

Input Schema

Name	Required	Description
`date`	No	Meeting day, YYYY-MM-DD, Australian Eastern time.
`venue`	No	Venue name as the feeds spell it, case-insensitive, e.g. Randwick or Sandown Hillside.
`country`	No	ISO country code(s), comma-separated: AU, NZ, GB (Britain, not UK), IE, ZA, e.g. 'AU' or 'GB,IE'. Without country or venue this covers AU, NZ, GB, IE and ZA.
`num_races`	No
`bookmakers`	No	Only these bookmaker keys, e.g. ["tab", "sportsbet", "ladbrokes_au"]. Default: every book. An unknown key is refused free of charge with the list of valid keys.
`categories`	No	Racing codes to include. horse = thoroughbreds. Default: all three.
`hours_ahead`	No	Scan window from now; default 6. Plan ceiling 24 / 48 / 168 as race_card.

Output Schema

Name	Required	Description	Default
`races`	Yes
`race_count`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 22, 2026

TDQS

A3.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare read-only/idempotent/open-world; the description goes well beyond by disclosing the pricing guards (books pricing under 100% excluded, quotes read before a scratching, placeholder prices never win), the credit cost, plan availability ('Every plan'), and that an unknown bookmaker key is refused free of charge with valid keys listed. These are exactly the behavioral facts an agent needs before calling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core return value, then the guards in parentheses, then the secondary metrics and the cost/plan line. Dense but every clause carries distinct information. The nested parenthetical is slightly run-on but no sentence is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return shape need not be spelled out, and the description covers the filter guards, cost, plan scope and default coverage. Remaining gap is scale/volume expectations (how many races/runners come back at default hours_ahead and num_races) and any rate limiting, which matter for a credit-charged, open-world call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 86%, so the schema already documents date, venue, country, bookmakers, categories and hours_ahead in detail. The description adds only the default coverage behavior ('without country or venue this covers AU, NZ, GB, IE and ZA'), which is largely restated in the country parameter description. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: best available win and place price for every runner in upcoming races, plus which bookmaker holds it, plus ancillary market metrics (book count, best-vs-worst spread, market percentage). That is clearly distinguishable from odds_board or race_odds in intent. It does not name the sibling it replaces or is replaced by, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is scope ('upcoming races', default 6-hour scan window, default AU/NZ/GB/IE/ZA coverage) but no explicit when-to-use versus odds_board, race_odds, consensus_price or closing_lines. An agent must infer from sibling names which tool answers which question. Cost ('3 credits') is stated but not framed as a usage trade-off against cheaper alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All puntersedge tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.