evaluate_steps

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

With readOnlyHint=true in annotations, the description goes beyond that by detailing the output behavior: it describes each step's columns, types, first rows, or the error. This adds meaningful context about what the tool returns, which is not captured in the annotation alone. No contradiction with the readOnlyHint.

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 tightly written in two sentences, with the core function and output immediately clear. The benefit statement is concise and adds value without redundancy. Every word earns its place.

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 tool with 5 parameters and no output schema, the description provides a good overview of the tool's purpose and output format, but leaves key parameter details (especially ignore_privacy_levels and timeout_seconds) unaddressed. The output structure is described in general terms but not precisely enough for an agent to know exactly what to expect without further context. It's adequate but not 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?

Schema description coverage is 0%, so the description must explain parameters. It only mentions `rows` (as 'first `rows` rows'), clarifying its role in limiting the displayed rows. However, it says nothing about source, query, timeout_seconds, or ignore_privacy_levels, leaving those ambiguous. This partial explanation does not adequately compensate for the lack of schema descriptions.

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 evaluates every step of a query in one call, listing exactly what it describes (columns, types, first rows, or error). It also distinguishes itself from evaluate_query by highlighting that it's a single call instead of one per step, making its purpose 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?

The description explicitly tells when to use this tool: to see how a query transforms data and find the first error step, framing it as faster than calling evaluate_query repeatedly. It clearly points to the alternative (evaluate_query) and the advantage, even if it doesn't list explicit conditions for when not to use it—the guidance is sufficient.

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