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

Annotations cover safety (readOnly, idempotent), but the description adds substantial domain semantics beyond them: it defines how is_overdue is computed, clarifies that partial_failure counts as failed for recent_failure_count, and warns that status does NOT reflect partial failures or the gap between failure and recovery. This is high-value behavioral context that annotations cannot provide.

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?

Front-loads the core purpose in the first clause, then layers definitions and usage guidance. It's dense but every sentence earns its place by clarifying non-obvious semantics (is_overdue, recent_failure_count, status). Slightly long, but justified by the complexity of the health signals.

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 fully explains the key return fields (last synced, next scheduled, outcome, is_overdue, recent_failure_count, status) and their edge cases. It also provides the critical caveat about relying on is_overdue and recent_failure_count over status. Complete for a zero-parameter list tool.

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?

Zero parameters, so baseline is 4 per the rubric. The description doesn't need to document parameters, and it appropriately focuses on output fields instead.

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?

Names the exact resource ('sync health for every cost/event/usage connection') and lists the specific fields returned (last synced time, next scheduled sync, outcome, is_overdue), which is far more specific than the name alone. An agent can distinguish this from siblings like list_cost_sources or list_anomalies without opening a schema.

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?

Explicitly routes usage: 'Check this before asserting that recent cost or usage data is complete, especially right before calling query_costs or query_usage for a very recent date range.' Names the condition and the downstream tools, which is exactly the when-to-use guidance needed.

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