generate_network_report

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does add useful context: defaults for dimensions and metrics, and the full list of valid values for both. It also specifies the account_name format and inclusive date range. However, it does not explicitly state that this is a read-only operation, does not mention any side effects, rate limits, or authentication needs, and does not describe the output format beyond what the output schema would provide. This is a moderate disclosure given the absence of 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?

The description is well-organized: a clear purpose sentence, followed by parameter format notes, then defaults and valid values. Every line contributes necessary information, and it is front-loaded with the main purpose. There is no redundant phrasing, and it uses line breaks to group related details, making it easy to scan.

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 that an output schema exists, the description does not need to detail return values. It covers all required parameters' formats and the optional parameters' defaults and allowed values. It does not mention any prerequisites like the need for a valid account from list_accounts, but that is implicitly available through sibling tools. The only gap is the lack of explanation for max_report_rows, but overall it is sufficient for an agent to call the tool correctly.

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 has 0% description coverage, so the description must compensate. It does explain the format for account_name ('accounts/pub-1234567890123456') and start_date/end_date ('YYYY-MM-DD', inclusive). It provides defaults and valid values for dimensions and metrics, which is beyond the schema. However, it does not explain the max_report_rows parameter at all, leaving it ambiguous. Overall, it adds significant meaning for most parameters but misses one.

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 it 'Generate an AdMob network (own ad serving) performance report.' The verb 'generate' plus the specific resource 'network performance report' is precise, and the parenthetical '(own ad serving)' distinguishes it from the sibling generate_mediation_report. An agent can immediately understand what this tool does.

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 explicitly scopes to 'network (own ad serving)', which implies it is for own ad serving reports as opposed to mediation. It provides the account_name format and date format, which are essential for usage. However, it does not explicitly name the alternative generate_mediation_report or state when not to use this tool, relying on the agent to infer the distinction from the scope.

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