keep_errors

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

With no annotations, the description must carry the full behavioral burden. It states that Table.SelectRowsWithErrors is appended to the M query, which is a useful concrete detail, but it does not disclose side effects, reversibility, or requirements like permissions. Basic behavior is covered, but not deeply.

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 compact and front-loaded, with three sentences each serving a distinct purpose: purpose, implementation, and parameter usage. There is no redundancy or wasted text.

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 covers the core behavior and implementation detail, but without annotations or an output schema, it does not explain prerequisites, potential side effects, or what happens when no errors exist. It is adequate for a simple operation but lacks depth for a mutating M query function.

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 input schema already describes the 'columns' and 'partitionName' parameters, and the description merely repeats the column usage. It adds no new meaning for the required 'table' and 'sessionId' parameters, leaving 50% of parameters without compensating explanation. The description adds minimal value beyond the 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 clearly states the tool's function with a specific verb ('keep') and resource ('rows that carry an error value'), and explicitly distinguishes it from related operations like remove_errors. The purpose is unambiguous and immediately understandable.

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?

The description implies usage ('to inspect bad data') and explains how to target columns, but it does not explicitly compare against alternatives like remove_errors or replace_errors, nor does it state when not to use this tool. It offers minimal guidance for selection among siblings.

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