cwv_diff_performance

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

No annotations are provided, so the description carries the full disclosure burden. It does add useful behavioral context by promising 'score deltas and diagnostic comparison' as outputs, and the 'compare' verb implies a read-only operation. However, it does not disclose whether network calls to the URLs occur, whether the operation has side effects, or what the response structure looks like. Decent but incomplete disclosure for an annotation-free tool.

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?

A single front-loaded sentence that names the verb, resource, accepted inputs, and output characteristics with zero filler. The input-format parenthetical earns its place by signaling flexibility, and every word contributes to the agent's decision about whether to invoke the tool.

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 two-string-parameter comparison tool with full schema coverage, the description is reasonably complete: it covers the operation, the input forms, and the output characteristics (score deltas, diagnostics). The only gap is the lack of an explicit return-structure statement, but since no output schema exists and the description hints at what the output contains, this is a minor omission rather than a blocking one.

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 100%, with both target_a ('Baseline URL, file path, or JSON audit string') and target_b ('Candidate/Optimized URL, file path, or JSON audit string') already documented. The description merely echoes these accepted forms without adding syntax, format, or usage details beyond the schema, so the baseline 3 for high coverage applies.

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 opens with a specific verb ('Compare') and a specific resource ('two performance audits'), and immediately names the three accepted input forms (URLs, files, audit results). The compare operation is clearly distinct from its siblings (cwv_audit_site audits, cwv_optimize_html optimizes, cwv_generate_* generates), so an agent can differentiate it without opening the schema.

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 accepted input forms (URLs, files, audit results) and the 'baseline vs. candidate/optimized' framing of the params imply when the tool is useful — comparing two performance states. However, there is no explicit guidance on when not to use it or how it relates to siblings such as cwv_audit_site (e.g., 'run cwv_audit_site first, then compare two results here'). Usage context is implied, not stated.

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