smithery-unicorn

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

No annotations provided, so description carries full burden. Only discloses output formatting constraints (narrative style). Fails to mention state mutation (stat changes via effects), game progression logic, or that omitting 'nextChallenge' ends the game—critical behavioral traits for a game engine tool.

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?

Three sentences, front-loaded with purpose followed by constraints. No redundant text—every sentence provides actionable guidance. 'IMPORTANT' flag effectively highlights critical constraint. Slightly terse opening could benefit from one more clause explaining this advances the game state.

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?

Complex tool with nested objects, 5 parameters, and conditional logic (month-gated stats). Lacks explanation of game loop mechanics, pivot system usage, or the relationship between 'chosenOptionId' and previous challenge options. No output schema compounds the gap—agent doesn't know if this returns updated game state or void.

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 80% with detailed field descriptions (e.g., 'Change to morale (only after month 3)'). Description adds value by reinforcing the narrative constraint ('Do NOT list or describe the next options'), which aligns with schema descriptions but emphasizes the UI separation pattern. Baseline appropriate for high schema coverage.

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?

Uses specific verb 'Resolve' with resource 'player choice', distinguishing from sibling 'start_game' (initialization vs. turn processing). However, 'Resolve player choice' is slightly vague about mechanical outcomes—doesn't clarify that this advances game state or modifies stats.

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?

Provides explicit behavioral constraints: 'Do NOT describe next challenge options in text' and 'Just narrate what happened.' Clear negative guidance prevents common errors. Missing explicit contrast with 'start_game' (when to use each), though implied by turn-based context.

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

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

With no annotations provided, the description carries the full burden. It discloses UI interaction patterns ('shown in the UI') and output constraints ('set the scene briefly'), but fails to mention state side effects (e.g., whether this creates a persistent game session, returns initial state, or can be idempotently retried).

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?

Extremely tight two-sentence structure. The first sentence states purpose; the second front-loads the critical constraint about UI options. Zero wasted words—every sentence earns its place by conveying essential behavioral information that cannot be inferred from the schema alone.

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?

Adequate but lean for a 7-parameter tool with nested objects and no output schema. The description covers the critical output formatting constraint, but given the lack of annotations and output schema, it could better prepare the agent by mentioning game state initialization behavior or what constitutes successful 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 86% (high), establishing a baseline of 3. The description references 'options' (relating to firstChallenge.options) to reinforce the constraint about not describing them in text, but does not add syntax, format details, or semantic meaning beyond what the well-documented schema already provides.

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 the tool 'Start[s] a new game' with a specific verb and resource. While the title '🦄 Start Unicorn or Bust' provides flavor context, the description itself effectively distinguishes from sibling 'play_turn' by emphasizing 'new game,' though it doesn't explicitly name the alternative.

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 provides explicit behavioral guidance: 'Do NOT describe options in your text response' and 'Just set the scene briefly.' However, it lacks explicit when/when-not guidance comparing against the sibling 'play_turn' tool, relying instead on the tool name to imply usage context.

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