moa_handoff_inbox

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

No annotations are present, so the description carries full responsibility. It discloses return fields (id/title/summary/state/fromProject), no context, newest-first ordering, hidden archived rows by default, exact matching semantics, empty result for misspelled addresses, and that handoffs never participate in recall/indexing. This is thorough behavioral disclosure.

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?

Four dense sentences, front-loaded with the main purpose. Each sentence provides meaningful detail (metadata, defaults, v2 filtering, indexing). The density is appropriate for the tool's complexity, though a slight bullet structure could improve scannability.

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?

With no output schema, the description defines the return shape by listing metadata fields and explicitly stating no context is included. It covers default filtering, exact state/agent matching, and error behavior. While it doesn't mention limit pagination, the schema handles that, making the description sufficient.

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 covers agent, workspace, and limit, but the description adds critical semantics absent from schema: state's default filter behavior (archived hidden), the v2 agent address behavior with empty-inbox error handling, and workspace scope clarification ('never infer a workspace from the MCP process cwd'). These additions go beyond the 75% schema coverage.

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 opens with a specific verb and resource: 'List handoffs addressed to the current project'. It clearly distinguishes from sibling tools like send, read, consume, and archive by focusing on listing. It also includes ordering and metadata scope, leaving no ambiguity about what the tool does.

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?

Provides explicit filtering guidance: archived rows hidden by default, pass state to filter exactly, and pass agent for toAgent filtering. It warns about misspelled agent addresses returning an empty inbox. It doesn't explicitly name alternative tools for 'when not to use', but the sibling names make this clear.

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