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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds genuinely useful behavior beyond them: the default date window behavior and the enumeration of valid data_level and breakdown values, which the schema does not constrain.

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-loaded with the core purpose, then compact sentences for dates, data_level, and breakdown. No filler. The parenthetical metrics list and pipe-delimited enums keep it dense and skimmable.

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?

The output schema exists so return values need no explanation, and the description covers the key inputs, defaults, and enum semantics an agent needs to call correctly. Only advertiser_id is left unexplained, which is a minor gap for a 5-param reporting 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?

Schema coverage is 0%, so the description carries the burden and does well: it documents date format, the default-30-day behavior, the data_level enum values, and the breakdown dimensions (splitting rows by demographic/placement). The one gap is advertiser_id, which is never mentioned, but the other four parameters gain real meaning.

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+resource ('TikTok performance report') and enumerates the metric families returned (spend/impressions/clicks/CTR/conversions). It clearly reads as a TikTok reporting tool, but does not explicitly name how it differs from siblings like microsoft_performance_report or performance_report.

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 reporting framing and the audience-collection nature of the tool, but there is no explicit when-to-use, when-not, or named alternative among the many report siblings. Defaults (empty dates = last 30 days) are helpful context but not routing guidance.

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