workload_compare

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description goes beyond that by detailing the comparison output (per-statement percentiles, throughput, errors, schema/row-count deltas) and scope (statement by statement), which meaningfully informs expected behavior.

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?

Two sentences, front-loaded with the core action followed by a usage scenario. Every clause contributes; there is no filler or repetition of structured fields.

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 correctly carries the burden of describing return content by listing the compared metrics. For a simple two-id read-only tool this is close to complete, though it could note prerequisites such as both runs needing to exist.

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%, and the two params (base_run_id, new_run_id) carry only titles. The description implies a baseline-vs-new pairing and before/after semantics, which partially compensates, but it never explicitly maps the identifiers to the base/new roles, leaving a gap.

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 states a specific verb and resource ('Compare two runs of a workload statement by statement') and enumerates what the comparison covers (p50/p95 before/after, percent change, throughput, errors, SQL/row-count changes). This clearly separates it from siblings like workload_run, workload_list, or workload_overview.

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 gives an explicit usage context and workflow: 'Use it to check a tuning change: run a baseline, change the table (sort key, shard key, index ...), run again, compare.' That is a concrete when-to-use, though it names no explicit alternatives or exclusions.

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