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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is established. The description adds genuinely useful scoping behavior: the list is bounded to a single project, omitting projectId changes the target to the personal project, and the result is paginated. The description's read-only wording is consistent with the annotations, and it clarifies that this is inherently a list-access, not a mutation, operation.

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 with zero filler. The essential abstraction boundary ("single project") is front-loaded, the invocation guidance on projectId and personal-project fallback follows logically, and the routing to the sibling comes last. For a 10-parameter tool, the description wisely delegates all filter details to the schema the schema already covers them richly.

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?

The description is complete for the selection problem: scope is specified exactly, and the 100% schema coverage plus read-only annotations cover the invocation contract. The primary gap is that there is no output schema and the description doesn't indicate the shape of each returned Riddle (e.g., whether these are summary objects or full Riddle payloads), which an agent invoking the tool fresh would need to learn by calling.

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% and the schema is exceptionally thorough on its own — the page parameter documents the 1-indexed, 12-per-page contract and rejection behavior, the origin parameter distinguishes the filter value from the returned per-Riddle object, and type/notType lists the valid enum values. The description only restates what the schema already says about projectId, adding no new parameter semantics beyond that.

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 states a specific verb and scope: "Returns a paginated list of Riddles from a single project." It goes beyond a generic 'lists riddles' by pinning the abstraction boundary — one project, not all projects — and explicitly names sibling riddle_account_list as the cross-project alternative. An agent can disambiguate this tool from its 60+ siblings from the first sentence.

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 an explicit usage context: use projectId for a specific project, omit it for the personal project, and "For Riddles across all projects, use riddle_account_list instead." This names the relevant alternative with the condition that selects it. It doesn't cover every alternative (e.g., when to use riddle_get for a single Riddle), but for the core scope decision it is fully explicit.

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