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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is fully covered. The description adds useful context about the lookback window and returned metrics, but does not describe response format, pagination, or failure behavior. This is helpful but not rich beyond annotations.

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 front-load the purpose, then list metrics, parameter details, and the alternative tool. Every sentence earns its place; the only redundancy is 'Read-only,' which mirrors the annotation but does not bloat the description.

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 one-optional-parameter read-only analytics call with no output schema, the description names all returned metrics, documents the window default and range, and gives an alternative. An agent can invoke it and interpret the response without needing further information.

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 coverage is 100% with a default, so the baseline is 3. The description adds the explicit range 1-365 and confirms that days controls the window, going beyond the schema's terse 'Lookback window in days'.

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 ('Get aggregate usage analytics over the organization's simulation runs'), enumerates the returned metrics, and explicitly frames this as aggregates versus individual runs. This makes it clearly distinguishable from list_runs and other siblings.

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 explicitly says 'Use list_runs for individual runs instead of aggregates,' giving a direct alternative and the condition that selects it. The aggregate-versus-individual contrast tells the agent when this tool is appropriate versus its closest sibling.

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