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

The annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds only the polling cadence and the fact that completion is reported; it says nothing about rate limits, auth requirements, or what happens after completion.

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 short sentences with the return payload front-loaded and the polling instruction immediately after. The trailing example largely duplicates the schema's examples block, which is mild redundancy but not bloat.

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 does the necessary work of describing the return shape (state counts, spend vs cap, completeness). What's missing is any note on terminal-state behavior or suggested stop condition for polling, which matters for a status-polling 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?

The single parameter has 100% schema description coverage ('From experiment_create'), so the schema carries the semantics. The description's example restates experiment_id without adding format or sourcing detail beyond what the schema already says.

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 names a specific resource (experiment) and enumerates exactly what it reports: cell counts by state, spend versus cap, and completion status. That enumeration clearly separates it from siblings like experiment_results, which returns outcomes rather than live progress.

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 states the trigger condition ('Poll this after experiment_create') and a cadence ('every few seconds'), which is concrete when-to-use guidance. It stops short of naming alternatives (e.g., when to prefer experiment_results or experiment_list) or an exclusion condition.

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