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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds meaningful behavior beyond that: the internal flow 'Takes name → looks up ID → fetches experiments tagged with budget group', the date semantics ('No dates = all-time data'), and the full list of returned metrics. It does not discuss error cases like unknown group names, but the added context is substantial.

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 longer than average but highly structured with clear sections: purpose, IMPORTANT, USE FOR, NOT FOR, HOW IT WORKS, METRICS RETURNED, and DATE HANDLING. It front-loads the core purpose and routing guidance. There is minor redundancy in repeating the 'name directly / no ID lookup' point, but overall each section earns its place.

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?

Given the tool has 7 parameters and no output schema, the description compensates well by listing the exact metrics returned, explaining the internal lookup flow, and covering date behavior. It does not define every metric name or explain pagination, but the schema handles those details. The definition is sufficiently complete for confident invocation.

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 baseline is 3. The description adds some helpful emphasis around budget_group_name (accepts name directly, no ID lookup required) and date handling, but most of that is already present in the schema property descriptions, which also cover pagination, sorting, and exclusion semantics. The description reinforces rather than meaningfully extends the schema.

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 precise specification: 'Performance statistics for a specific budget group by name.' It then enumerates the exact metric categories returned and explicitly distinguishes itself from get_budget_group, list_budget_groups, experiment_performance_stats, and account_level_stats, so an agent can tell it apart from its nearest siblings without opening schemas.

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?

The description provides explicit USE FOR and NOT FOR sections, names the exact alternatives for excluded cases, and adds a direct workflow instruction: 'Do NOT call get_budget_group before this tool.' This leaves no ambiguity about when to select this tool versus its siblings.

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