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

The description adds significant behavioral context beyond the readOnlyHint and idempotentHint annotations: it warns that draft/unpublished changes and disabled areas are excluded, notes that internal IDs are stripped, and defines the shape for empty projects. These details prevent an agent from misinterpreting an empty result or expecting unpublished state, which annotations alone cannot convey.

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?

The description is long but every segment earns its place: it defines the main purpose, narrows to published/enabled defaults, excludes draft and disabled content, clarifies ID stripping, pins down the output type, and gives usage routing to a sibling. The main result is front-loaded and the caveats are organized logically.

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 read-only single-parameter tool with no output schema, the description provides a full picture: what is returned, what is deliberately omitted, how edge cases (empty settings) are represented, and when to use it relative to alternative tools. Agents large can invoke and interpret this tool correctly without needing additional context.

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?

The input schema is concise with 100% coverage for the single projectId parameter, whose description already states it is the project whose defaults are returned. The tool description does not need to add much to parameter semantics because the schema fully documents it; the description's value lies in outputs and behavior rather than parameter details.

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 the tool returns the project's default Riddle settings, specifying exactly which settings are included (published and enabled only). It clearly differentiates from sibling project_get by noting that the latter gets a project's name, image, and permissions instead. The resource and intent are unmistakable.

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 explicitly tells the agent when to use this tool (before creating or editing a Riddle to understand forced defaults) and points to project_get as the lightweight alternative for core project metadata. It also states what the tool deliberately does not do—inspect unpublished or disabled defaults—removing ambiguity about edge cases.

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