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

Annotations already mark it read-only and non-destructive; the description adds non-obvious behavior such as the hard limit of 1000 rows per page, the recommendation to page with offset until a short page, and automatic profile-tenancy enforcement. It does not describe default ordering or exact response shape, but the main operational behaviors are disclosed.

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 dense but economical; every clause carries a distinct fact (fidelity, projection, filters, dates, ordering, pagination, use cases, tenancy). It is front-loaded with the core purpose. A slight structural cost comes from one long multi-clause sentence, but there is no filler.

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 a complex 10-parameter tool with no output schema and weak schema descriptions, this description covers the essential invocation details: pagination strategy, supported operators, use cases, and tenancy. The main remaining gaps are exact date formats and filter-object syntax, and what the returned rows look like, but the basic contract is clear.

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?

Schema coverage is only 10%, so the description must compensate. It maps nearly every parameter family to a capability: column projection, filters with operator list, date bounds, ordering, and limit/offset, plus dataset_key via ppc_describe and profile_id via tenancy enforcement. It stops short of showing the exact JSON shape for filters, but it adds substantial meaning beyond the bare schema.

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 opens with a specific action ('FULL-fidelity row-level query') and a concrete resource ('any raw PPC dataset'), and it explicitly separates itself from the shaped ppc_* readers, which are said to cap certain data. It also points to ppc_describe for dataset discovery, making the tool's niche unmistakable.

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 gives concrete conditions for choosing this tool: daily time series below account level, SB/SD keyword-level data, and anything the shaped ppc_* readers cap. It does not enumerate when to prefer specific alternative named tools, but the shaped-reader exclusion gives usable routing guidance.

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