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 covered structurally. The description adds value by disclosing that default Riddle settings are NOT returned and explains why ('large nested configuration tree that is rarely what a caller wants'), providing behavioral context beyond the annotation fields.

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, zero waste: sentence one states purpose and return shape, sentence two explains ID provenance, sentence three discloses the exclusion with rationale and redirects. Perfect front-loading of the core verb+object in the first words. Every clause earns its place.

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 single-parameter read-only getter with no output schema, the description is thorough: it lists return fields, gives input provenance, and anticipates the most likely surprise (missing settings) with a pointer to the right tool. Slight room remains for error-handling or authorization context, but nothing critical is missing for this simple operation.

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% with the parameter described as 'The ID of the project to look up,' establishing the baseline of 3. The description adds genuine value above this by explaining where to obtain the projectId (project list tool or riddle_get's 'team' property), which is semantic provenance not present in the 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?

Specific verb+resource: 'Returns a single project by its project ID' with explicit return fields (id, name, image, permission matrix). Clearly distinguishes from siblings by name-dropping project_get_settings and project list, and clarifies this returns a single project versus the plural-focused list tools.

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?

Explicit when-to-use guidance: tells callers how to source the projectId (project list tool or riddle_get's 'team' property) and explicitly redirects users away for settings ('use project_get_settings for them'). This is exactly the kind of exclusion-and-alternative guidance the rubric rewards.

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