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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so the safety profile is covered. The description still adds substantial non-annotation behavior—async queued query with wait_seconds, timeout convergence on the same query, metering identical to query_run, rerun-on-limit via query_run, and untrusted_provider_content labeling—which is real value, though the structure is dense enough that the key operational caveats are easy to miss.

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?

Front-loaded with the core behavior and the example payload anchors usage early, so an agent gets the essentials in the first two sentences. The tail is long, but nearly every sentence covers a distinct failure mode, retry path, or metering rule rather than restating structured data.

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 supplies the full return shape (operation, table_version_id, rows of value/row_count, truncated, untrusted_provider_content) plus every documented error state and the correct recovery call for each. Nothing material to invoking or recovering this tool is left implicit.

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 description coverage is 0%, so the description must carry the parameter burden, and it does for most: limit (default 20, max 200), prefix (case-insensitive starts-with), wait_seconds (default 10, max 20), column (must be declared or it is refused by name), and table_id via the example. table_version_id and search_revision_id are never explained as inputs, leaving two of seven parameters undocumented.

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?

States a precise verb, resource and scope: the most frequent non-null values of one declared column of a sealed table version, with row counts, most-frequent first. This sharply distinguishes it from value-returning siblings like sample_rows or query_table, and the later 'use query_run over the run that built the version instead' line marks the boundary against query_run.

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 when to use it ('choose filterable columns, check a value dictionary or write a plan's predicate values from values that exist') and gives conditional routing for edge cases: retry the same call on query_timed_out, retry after retry_after_seconds on query_unavailable, and fall back to query_run on capability_unavailable.

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