Skip to main content
Glama

Prediction Markets Quant

by com.predictionmarketspicks

Who Do I Draft?

who_do_i_draft
Read-only

Recommend the single best player to draft right now given the roster already on the user's team and their pick number, weighing positional need against the best value available (2026, any scoring format). The pick itself is always free, no key. One email adds alternatives; Pro adds the full reasoning. Prefer this mid-draft when the user asks "who should I take", "who do I draft", "what do I need". Input: roster (names on their team), pick_number, and optionally drafted (names already gone). Without drafted, the board is estimated from pick_number using consensus ADP. Returns one pick + a one-line reason.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
teamsNoLeague size (number of teams) for draft-round math. Overrides the platform default; falls back to 12.
rosterYesPlayer names already on the user's team.
draftedNoPlayer names already drafted by ANY team. Optional — without it the board is estimated from pick_number using consensus ADP. Supplying it is always more accurate.
scoringNoScoring format: standard, half_ppr (default), or ppr (full PPR). Overrides a platform preset. Works for Yahoo/ESPN/Sleeper defaults.
platformNoLeague platform — applies its default scoring, size, roster + best-ball settings (overridable by explicit scoring/teams). Underdog/DraftKings are best ball.
pick_numberYesThe overall pick number on the clock.

TDQS

A4.3/5.0
Behavior4/5

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

Annotations declare readOnlyHint=true and openWorldHint=false, which already signal a safe, bounded read operation. The description adds meaningful behavioral context beyond that: the pick is 'always free, no key', drafted is optional and the board is 'estimated from pick_number using consensus ADP' when omitted, and the output is 'one pick + a one-line reason'. No contradiction exists with 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.

Conciseness4/5

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

The description is dense but organized: purpose first, then behavior, usage triggers, input semantics, fallback behavior, and return format. The trigger-phrase list is slightly redundant but useful for routing, and no sentence is pure filler. It earns a 4 rather than a 5 because the pricing/plan detail ('One email adds alternatives...') is tangential to correctly invoking the tool.

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?

With no output schema, the description correctly specifies the return shape: 'Returns one pick + a one-line reason'. It also covers the optional drafted behavior and scoring/platform defaults. It is slightly incomplete in that it never mentions minimum roster constraints or what happens for edge cases like an empty roster, but for a recommendation tool it gives enough to call it correctly.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3, but the description adds real semantic value. It clarifies that roster means 'names on their team', drafted means 'already drafted by ANY team', and that supplying drafted is 'always more accurate' because the board is estimated from ADP otherwise. It also explains how platform and scoring defaults interlock.

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

Purpose5/5

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

The description opens with a specific verb and resource: 'Recommend the single best player to draft right now', further scoped by roster, pick number, positional need, and value. This clearly distinguishes it from companion tools like best_available, which would be broader, and draft_board, which would not produce a single pick.

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

Usage Guidelines4/5

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

The description explicitly states when to use the tool: 'Prefer this mid-draft when the user asks "who should I take", "who do I draft", "what do I need"'. It does not name alternative sibling tools or give when-not-to-use conditions, but the trigger phrases and mid-draft context are clear enough for an agent to route correctly.

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

All Prediction Markets Quant toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation3/5

Many tools have clearly distinct domains (fantasy vs NFL vs commodities vs general mispricings), but the 'edge' family is crowded: calculate_ev, scan_mispricings, edge_alerts, find_arbitrage, commodity_edge, nfl_edge, and nfl_prop_edge all surface pricing edges in overlapping ways. Fantasy tools like best_available and who_do_i_draft also have very similar mid-draft recommendation purposes, though their inputs differ.

Naming Consistency4/5

All tool names use lowercase snake_case and are readable, but they mix verb_noun patterns (calculate_ev, compare_players, scan_mispricings) with noun-phrase names (adp_market_gaps, edge_alerts, kelly_size, market_pulse). The style is consistent enough that an agent can predict the convention, with only minor deviations from a strict verb-first pattern.

Tool Count3/5

23 tools is on the heavy side for a single MCP server, though the scope is genuinely broad: prediction-market edge detection, position sizing, probability math, and fantasy football draft tools. It is not bloated enough to feel chaotic, but several tools could be consolidated or are tier-gated variants of the same underlying data.

Completeness4/5

The fantasy football surface covers the draft lifecycle well: rankings, player outlooks, comparisons, ADP gaps, and in-draft recommendations. The prediction-market side covers edge detection, EV, Kelly sizing, base-rate comparison, and arbitrage discovery, though it lacks direct market-price fetching or portfolio tracking—minor gaps that users can work around by supplying prices themselves.

Resources