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

Beyond the readOnly and idempotent annotations, the description explains the waiting behavior, the 25-second wait cap, the meaning of a pending return, and that pending is success. It also explicitly states that the call does not change the handoff, which is valuable behavioral context.

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 short and front-loaded with the core wait behavior. Every sentence adds useful operational detail: return semantics, pending success, retry behavior, non-mutation, and when to prefer the Tasks extension.

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 two-parameter read-only tool with no output schema, the description covers the important return semantics and retry behavior. It also explains when to use it versus the Tasks-based approach, leaving no major operational gap.

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 description coverage is 100%, so the id and timeout_ms parameters are already documented in the input schema. The description mentions the 25-second wait window but adds little parameter-specific guidance beyond the schema's range and default for timeout_ms.

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 resource: wait up to 25 seconds for one handoff on this account. It clarifies that it returns the completed result or a pending status, which distinguishes it from simple status/result retrieval. However, it does not explicitly name get_handoff_result or get_handoff_status as alternatives, so sibling differentiation is implied rather than fully explicit.

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?

It gives an explicit usage condition: use it when the client does not declare the MCP Tasks extension. It also names the alternative behavior with Tasks: pass await_answer on send instead, and explains that repeated calls are needed to keep waiting.

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