perf_diff

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

No annotations are provided, so the description must handle behavioral transparency. It does disclose that both files must be from perf record with compatible events and describes the output format. However, it does not explicitly state whether the operation is read-only or has any side effects, which is a gap without annotations.

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 concise and well-organized: it starts with the core purpose, follows with a usage sentence, a recognizable list of key parameters, the output format, and then a constraint. Every sentence adds information and there is 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 covers the essential output (differential table with columns) and the prerequisite (compatible events), which is important given the large schema and no provided output schema. It doesn't explain every parameter, but it highlights the key ones and gives enough context to successfully invoke the tool.

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 schema has 100% description coverage, giving a baseline of 3. The description adds value by clearly identifying old_input as baseline and new_input as comparison, and by expanding the compute parameter with valid methods ('delta', 'delta-abs', 'ratio', 'wdiff', 'cycles'), which goes beyond the schema's generic 'Comparison method' label.

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 that the tool compares two perf.data profiles side by side and shows per-symbol overhead changes between baseline and new measurement. It also mentions concrete use cases (optimization validation, regression detection, A/B testing), which distinctly positions it against siblings like perf_report or perf_annotate.

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 instructs when to use the tool: 'Use this for before/after comparisons — optimization validation, regression detection, or A/B testing.' This gives clear context, though it does not explicitly mention when not to use it or name alternative tools, so a score of 4 is appropriate.

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