uprof_compare

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

With no annotations, the description fully discloses the verdict logic: failure when total or significant function regresses beyond threshold_pct, noise floor exclusion, and the fail_on_regression error behavior. This is crucial for automated use.

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 three sentences, front-loaded with the core purpose, then context, then behavioral details. Every sentence contributes value with no redundancy.

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 fully covers the tool's behavior, parameter semantics, and usage context. An output schema exists, so return values need not be described. It is complete for the tool's complexity.

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 adds meaning to all parameters: threshold_pct and noise_floor_pct are explained in the verdict logic, fail_on_regression is described as raising a tool error, and baseline_id/candidate_id are implied by the compare operation. This compensates for the 0% schema coverage.

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 compares two stored results function-by-function and issues a pass/fail verdict. This specific verb+resource distinguishes it from sibling tools like uprof_collect or uprof_report_raw.

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 positions the tool as the core of an optimize loop, explaining when to use it after collecting baseline and candidate. It also explains how to gate automated loops with fail_on_regression, but does not explicitly name alternatives or exclusions.

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