Help and Next Steps

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

Annotations already mark it read-only and non-destructive; the description adds important context beyond those annotations by stating that auth is not required, it inspects session state without making API calls, and errors are effectively none. This gives the agent strong confidence that calling this tool is safe and side-effect-free. No contradiction with annotations exists.

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 compact and front-loaded: the core orientation purpose comes first, followed by clearly labeled Auth, Errors, and Related notes. Each sentence contributes necessary information about scope, safety, or next steps, with no filler or repetition.

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 zero-required-parameter help/orientation tool with strong annotations, the description covers purpose, side-effect profile, error behavior, and the relationship to recipe execution. The absence of an output schema is not a significant gap because the description already tells the agent what the tool produces: recommendations for next calls and recipes.

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 single optional `goal` parameter is fully documented in the schema with an enum and clear guidance to omit it or use `auto`, so schema coverage is effectively 100%. The description reinforces the parameter's purpose through session-state recommendation context but adds no new syntax, constraints, or semantics beyond 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?

The description identifies a specific resource ('this MCP server') and a concrete outcome: explaining the three Ethora auth modes and recommending next tool calls/recipes based on session state. It does not merely restate the title, and no sibling tool claims this orientation/next-step role.

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 use case is implied: call this when orientation or next-step recommendations are needed, and it even points to ethora-run-recipe for recipe execution. However, it never explicitly states when not to use it or names alternative introspection/status tools such as ethora-status or ethora-doctor, so selection guidance is implicit rather than explicit.

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