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

Annotations carry only idempotentHint=false, so the description correctly shoulders most of the behavioral burden. It discloses the exact error for connecting drafts, introduces the return value ('the compact build-configuration envelope of riddle_get') and explains the 'queued': true flag when queue is set. It stops short of stating that every call creates a new Riddle, though the annotation already signals non-idempotence.

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, each serving a distinct purpose: the core action, full-option documentation pointer, and response-shape contract. The opening sentence front-loads purpose and constraints. The embedded URL and reference token (riddle://...) are slightly dense but earn their place by pointing the agent at canonical detail.

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 tool with one nested parameter, no output schema, and a single annotation, the description covers the essentials: what it builds, what it can connect, the draft failure mode, and the shape of the response including the queue edge case. It relies on an external reference for the full response format, which is acceptable; a native sketch of the return envelope would have made it fully self-contained.

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%, so the baseline is met by the schema's already-detailed parameter texts (especially for 'omit', 'build', and 'templateId'). The description adds some linkage — showing that 'omit' mirrors riddle_get and that selecting 'queue' modifies the response envelope — but does not itself carry per-parameter semantics beyond that. This is an adequate division of labor with the parameter schema.

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?

Description opens with a specific verb+resource ('Builds a Leaderboard from a build configuration') that immediately distinguishes it from the many sibling builder tools (quiz, poll, predictor, story, etc.). It further sharpens the scope by stating what counts as connectable content ('quizzes, predictors or minigames (except WheelSpinner exclusive ones)... that have Name and Email fields'), and cites the exact failure mode for drafts. This is unambiguous and distinctive within a large sibling family.

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 gives clear contextual conditions for use: connected targets must have Name/Email fields, must already be published, and WheelSpinner-only minigames cannot be connected — with the failure message quoted. It does not, however, explicitly say 'use riddle_builder_quiz instead for building a quiz' or otherwise rule out this tool in favor of a named alternative, so the when-not-to-use guidance is left slightly implicit.

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