Read one Texas Hold'em hand on a 3-5 card board: the made hand (category and label) plus every draw with its out count.
| Name | Required | Description | Default |
|---|---|---|---|
| hand | Yes | Two cards, e.g. "Jh Th" | |
| board | Yes | 3-5 community cards, e.g. "9h 8h 2c" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It accurately discloses the operation is a read/analysis and specifies the output granularity (category, label, draws, out counts). However, it does not reveal the return structure (how made hand vs. draws are formatted), edge cases (e.g., duplicate cards, 3 vs 5 card board handling), or how overlapping draws are reported. Core behavior is disclosed, but output-format and boundary details are absent.
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?
A single sentence, zero filler. The verb and scope lead immediately, followed by a colon-delimited enumeration of outputs. Every clause earns its place, and the length is proportionate to the information being conveyed.
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?
For a 2-parameter tool with no output schema and no annotations, the description covers the essential selection and invocation facts: inputs (schema-covered), scope (3-5 card board), and outputs (made hand + draws with out counts). The minor gap — no explicit description of the result structure — is softened because the agent can infer the output from the enumerated elements. Slightly above adequate.
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 100%, with both 'hand' and 'board' documented with formats and examples in the schema, so the baseline is 3. The description reinforces the 3-5 card board constraint but adds no new parameter-level semantics — it explains what the analysis produces rather than adding meaning to the inputs. The schema already carries the load, so no penalty and no bonus.
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 opens with a specific verb ('Read') and resource ('one Texas Hold'em hand'), then enumerates the exact outputs: the made hand (category and label) and every draw with its out count. This precision distinguishes it from siblings calculate_equity (numeric equity) and calculate_pot_odds (odds comparison) without needing to inspect their schemas.
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 makes the input preconditions explicit — a hand and a 3-5 card board — which tells the agent when this tool applies (analyzing a board that has already run out). It clearly implies use for structural hand evaluation as opposed to the numeric outputs of its siblings, though it never names those alternatives or states explicit exclusions. The context is clear but the routing is left to inference.
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.
Each tool addresses a clearly distinct poker question: hand/draw identification, equity comparison between specific hands, and pot-odds call decision. There is no functional overlap between the three tools.
All tool names follow a consistent verb_noun pattern using lowercase snake_case, with 'analyze_hand' and two 'calculate_*' tools. The naming convention is uniform and predictable.
Three tools is a well-scoped count for a focused poker calculator server. Each tool covers an essential task without redundancy or bloat.
The set covers the core poker workflow: reading a hand, comparing equity, and evaluating pot odds, with useful cross-references between tools. A minor gap is that equity only supports specific hands rather than ranges, and analyze_hand is limited to Texas Hold'em while calculate_equity also handles Omaha.
