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

Annotations already establish readOnly=true, destructive=false, openWorld=false, so the safety profile is covered. The description usefully adds that the group ID is resolved internally and that only one page of experiment-level data is returned, which is real behavioral context beyond structured fields. The page-size cap repeats the schema's maximum of 100, so it adds little.

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?

Two tight sentences with zero filler. The identification mechanism and return shape are front-loaded, and the pagination limit is stated last where it belongs.

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 seven parameters but full schema coverage and no output schema, the description adequately conveys the return shape ('one page of experiment performance data with the available pagination metadata'). Minor residual gap: no hint about what happens when a budget group name is ambiguous or not found.

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 every parameter including page, size, sort, date range, and excludeExperimentName is already documented in the schema; the baseline of 3 applies. The description only reinforces that identification is by name and that results are paged, adding no format or semantics beyond 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?

States a specific verb (read) and resource (performance statistics for a budget group), plus the key detail that the group is identified by name rather than ID. This distinguishes it from get_budget_group (group definition) and the generic performance_metrics/account_level_stats siblings, though it does not name any of them explicitly.

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?

Usage is implied by the read-performance framing and the note that the group ID is resolved internally, which tells the agent it doesn't need a lookup step first. There is no explicit when-to-use guidance versus get_budget_group, experiment_performance_stats, or account_level_stats, so the selection decision is left partly to inference.

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