query_table

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

With no annotations provided, the description carries the full burden and does an excellent job: it declares read-only behavior, states that only SELECT is permitted, clarifies the query can never modify saved data, and explains that original data remains untouched unless the save_as name deliberately targets the original table.

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 well-structured: the main purpose and safety context come first, followed by a realistic example and a practical save_as workflow. It is slightly longer than necessary due to some restatement of safety guarantees, but every key concept contributes meaningfully.

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?

The description is strong for primary behavior and saving results, but it leaves out the max_rows semantic, which is important for agents deciding whether they will receive all matching rows or only a capped page. Given an output schema exists, return values are not needed, but the parameter gap prevents this from being fully complete.

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 description gives strong, concrete meaning to sql and save_as through an example and workflow explanation. However, schema description coverage is 0% and max_rows is never mentioned, so the 200-row default limit and its impact on returned output are left 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?

The description uses a specific action, 'Run a read-only SQL SELECT', and names the exact resource, 'saved result tables'. It distinguishes itself from extraction and export siblings by focusing on in-place analysis with filters, aggregation, and grouping, and it explicitly says it is how you analyse a large scrape.

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 clearly states when to use it: when you need to analyse a large scrape without pulling all data into the conversation. It also gives a clear workflow for saving cleaned results with save_as. However, it does not explicitly name alternative tools like get_table or list_tables for cases where this tool is not the right fit.

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