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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial context beyond them: the 100-row max_rows cap, the 16 KiB trim with rows_omitted, the 20s wait_seconds cap, the query_timed_out/query_id continuation contract, and the untrusted_provider_content labelling with an all-caps instruction to treat it as evidence not instructions.

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 and dense with no filler — every clause carries a constraint, cap, or routing hint. It is long and em-dash-heavy, with the untrusted_provider_content note trailing at the end, but nothing is truly redundant.

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?

Even without an output schema, the description enumerates the return shape ({query_id, state, rows, row_count, truncated, elapsed_ms, result_digest}) and the failure shape (query_timed_out), plus caps and the untrusted-content wrapper. An agent can call this and interpret the result without further sources.

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 load and does: it defines sql's dialect and required leading keyword, max_rows' cap, wait_seconds' cap, and query_id's role as a no-sql continuation handle. run_id is only implicitly identified as the sealed run's id, a minor gap given the 0% coverage starting point.

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?

Opens with a precise verb+resource+scope: 'Runs one read-only SQL statement over the parquet a run sealed, and waits for the answer.' This is clearly distinguishable from siblings like query_table (arbitrary tables) and get_artifact_download (bulk retrieval), and the read-only/single-statement limits are stated up front.

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?

Gives an explicit when: 'THIS IS HOW YOU CHECK THE DATA IS RIGHT before promoting anything: count the rows, look at the range, find the nulls,' which ties it to the promote_table workflow. It also routes the agent away from paging to get_artifact_download, and explains the timeout/query_id reuse path so a second statement isn't run.

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