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

Annotations declare readOnlyHint=true, destructiveHint=false, so the tool is safe to call. The description adds useful context like the CONVO/MESSAGE ad caveat, warning that clicks/ctr/cpc are typically 0 for those ad types. However, it contains a significant behavioral inconsistency: it states timeframe can be 'MONTH' but the schema enum only allows QUARTER, WEEK, YEAR. This misleads the agent about accepted values and default behavior, undermining transparency.

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 well-structured with clear sections (USE FOR, NOT FOR, CHANNELS, TIMEFRAME LOGIC, CUSTOM DATE RANGE, METRICS, CONVO/MESSAGE AD CAVEAT). It is front-loaded with the core purpose and usage guidance. It is somewhat long, but the length is justified by the detailed caveat and metric listing. Every section serves a purpose, though the flawed timeframe logic could be considered unnecessary or misleading.

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?

There is no output schema, so the description must explain what is returned. It lists available metrics and the CONVO/MESSAGE caveat, which helps. However, it does not specify the response structure or how to select a channel (despite listing CHANNELS), and the timeframe discrepancy leaves the agent uncertain about valid inputs. Given the tool's complexity and absence of output schema, these gaps make the description incomplete.

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 schema already provides detailed descriptions for startDate, endDate, and timeframe (100% coverage). The description adds timeframe logic and custom date range rules, but the timeframe mapping includes 'MONTH' which is not in the enum, so the added semantics are incorrect. It also mentions CHANNELS (FACEBOOK, LINKEDIN, GOOGLE ADS, ALL) but does not explain how to specify a channel given the schema has no channel parameter, leaving a semantic gap.

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 clearly states the tool's purpose: 'Account-level statistics and channel breakdown for a timeframe.' It also explicitly differentiates from sibling tools by stating 'NOT FOR: Campaign-level info (use experiment_performance_stats), specific experiments (use get_experiments).' This gives a specific verb, resource, and scope, and distinguishes it from alternatives.

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, naming alternative tools for other scopes. It also gives detailed timeframe logic and custom date range instructions. However, the timeframe logic includes a mapping to 'MONTH' which is not present in the schema's enum (which only has QUARTER, WEEK, YEAR), creating potential confusion about when and how to use the timeframe parameter. This inconsistency reduces the clarity of usage instructions.

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