Read from the account

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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses that cost is checked before the call, that state-changing calls are refused, and that some read methods return misleadingly empty-looking results without the right field names. It also flags return-type quirks for specific methods.

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?

Every sentence earns its place: the core call pattern and write exclusion come first, followed by cost semantics and known traps. It is dense but well organized, with no repetition of schema fields or annotation details.

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?

For an open-world read wrapper with no output schema, the description covers invocation, refusal behavior, cost semantics, and the most common empty-result traps. It also tells the agent to read knowledge://traps first, which is the right pre-flight step for this 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?

The input schema already covers all four parameters at 100%, so the baseline is 3. The description adds value by giving dotted method examples such as keywordsresearch.hassearchvolume, extra service names like dictionaries, and clarifying the meaning or shape of results for those calls.

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 explicitly states the tool calls any reading method of Direct API v501, gives concrete examples like campaigns.get, ads.get, and keywords.get, and distinguishes itself by refusing state-changing operations. It clearly separates this tool from write-capable siblings.

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?

It provides a clear when-to-use rule: call it for any reading method. It also gives an explicit when-not-to-use rule: state changes go through direct_plan and direct_apply. The pointer to knowledge://traps before use is additional concrete guidance.

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