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

The annotations already declare readOnlyHint and no destructive behavior, and the description adds meaningful behavioral detail: it never returns query results, only a catalog or column list plus a sample row for a selected dataset. It also discloses the scope of covered datasets. No contradiction with 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 a single dense sentence with no filler, and it front-loads the two invocation modes. The parenthetical list of dataset categories is useful but makes the description longer than strictly necessary.

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?

With no output schema, the description still explains what the agent will get in both modes: a catalog, or a column list plus sample row. It also specifies the dataset scope and granularity, so an agent has enough context to invoke the tool and interpret the result 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?

profile_id is well described in the schema, and dataset_key has no schema description, so the description must compensate. It explains that dataset_key selects a dataset and changes the output, but it does not enumerate valid keys or provide examples; the no-argument catalog is the implied way to discover them. This is adequate but has a clear 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 identifies a specific action (describe/catalog) and resource (raw PPC datasets behind ppc_query), and distinguishes the two operating modes. It also orients the tool relative to ppc_query, so an agent can tell this is schema discovery rather than data querying.

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 explicitly states when to use the no-argument form (return a catalog) versus the dataset_key form (return columns and a sample row), which is clear contextual guidance. It does not name sibling alternatives or state when not to use it, so it stops short of full routing guidance.

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