Seed Demo Ad Portfolio

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

Annotations indicate readOnlyHint=false, destructiveHint=false, which aligns with description stating it appends new portfolio each call (non-destructive, non-read-only). Description adds details on idempotency (not fully idempotent but safe to repeat) and data scope (240 rows). Minor point: could mention performance or call limits, but adequate.

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?

Three sentences packed with useful information: purpose, contents, usage guidance. No wasted words. Could be slightly more concise by removing 'for trying AdOps without real data' but still efficient.

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?

Description covers purpose, contents, usage alternatives, and safety. No output schema, but description mentions what's created. With no parameters, there's little else to add. Complete enough for intended demo use.

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?

No parameters in schema, so description doesn't need to explain them. Description mentions what's seeded (connections, campaigns, metrics) but doesn't miss anything since there are no parameters. Baseline 4 for zero-param tool is appropriate.

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?

Clearly states it creates a realistic cross-platform ad portfolio for testing, with specific details on contents (2 connections, 8 campaigns, 240 rows, alerts). Distinguished from sibling tools like ad_csv_import and platform_connect.

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?

Explicitly says use this for exploration (demo), then switch to ad_csv_import for production with real data. Also notes it's safe to call multiple times, providing clear guidance on when and how to use.

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