Career aggregate statistics for a player (men's and women's cricket) from Cricsheet ball-by-ball archives: innings, runs, strike rate, average, high score, wickets, economy — per format.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | player name, e.g. 'Rachin Ravindra' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered and nothing is contradicted. The description adds valuable context beyond annotations: data provenance (Cricsheet ball-by-ball archives), gender coverage (men's and women's), and per-format aggregation behavior — all non-obvious traits the agent would not know otherwise.
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 front-loaded sentence: purpose leads, followed by source, stat list, and the per-format qualifier. There is no filler, no repetition of schema content, and every clause adds information an agent needs to select and invoke the tool.
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 one-parameter read-only tool with no output schema, the description covers scope, data source, returned fields, and per-format grouping — enough to form an accurate mental model of the result. Minor gaps are the lack of explicit return-structure detail and name-matching behavior for unknown or ambiguous players, but these are unlikely to block correct invocation.
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 description coverage is 100% — the single `name` parameter already has a description with a concrete example ('Rachin Ravindra'). The tool description adds no parameter-specific meaning beyond what the schema provides, so the baseline 3 applies.
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 names a precise scope — 'Career aggregate statistics for a player' — with a specific resource (player), a concrete stat list (innings, runs, strike rate, average, high score, wickets, economy), and per-format grouping. The single-player career framing differentiates it from siblings like cricket_head_to_head (two players), cricket_leaders (rankings), and cricket_phase_stats 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?
When to use the tool is implied by the purpose statement — when an agent needs career aggregates for a single player — but no explicit when/when-not guidance or alternative tools are named. An agent must infer that head-to-head comparisons belong to cricket_head_to_head or that phase-level breakdowns belong to cricket_phase_stats.
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 targets a distinguishable cricket data need: reference, match status, archives, player splits, team/venue stats, and probability. The only mild overlap is cricket_market_odds and cricket_win_probability, both returning probability-like output, but their descriptions make the market-vs-model distinction clear enough.
All tools share the cricket_ prefix and mostly use descriptive noun phrases such as cricket_player_career and cricket_venue_stats. cricket_explain_term breaks the pattern slightly as the only verb-led name, so the set is highly consistent but not perfectly uniform.
Eleven tools is well within the ideal range for a domain-specific cricket data server. Each tool covers a meaningful slice of the domain—explainer, live matches, archived scorecards, player/team/venue stats, leaderboards, and probabilities—without feeling bloated.
The surface covers most core cricket analytics workflows: lookup, live scores, career and phase stats, head-to-heads, team form, venue behavior, leaderboards, and win probability. Minor gaps exist such as detailed live ball-by-ball commentary or series-level schedules, but agents can generally accomplish common cricket questions without dead ends.